Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 478 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4694. Min Range: -12.4694
Max Act: 12.4694. Min Act: -0.1698
Data Index: 4795837 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4694. Min Range: -12.4694
Max Act: 12.2819. Min Act: -0.1700
Data Index: 4795824 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.9069. Min Act: -0.1700
Data Index: 4795839 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.9069. Min Act: -0.1700
Data Index: 7969780 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.7819. Min Act: -0.1700
Data Index: 4795833 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.8444. Min Act: -0.1700
Data Index: 4795821 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.7819. Min Act: -0.1699
Data Index: 4795818 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.7819. Min Act: -0.1700
Data Index: 4795823 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.7194. Min Act: -0.1700
Data Index: 4795825 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.7194. Min Act: -0.1700
Data Index: 4795835 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.5319. Min Act: -0.1700
Data Index: 4795842 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.5319. Min Act: -0.1700
Data Index: 4795819 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.4694. Min Act: -0.1700
Data Index: 5253319 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.4069. Min Act: -0.1700
Data Index: 4795829 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.4069. Min Act: -0.1700
Data Index: 7838085 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.2194. Min Act: -0.1700
Data Index: 4795831 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.1569. Min Act: -0.1700
Data Index: 4795836 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.0944. Min Act: -0.1700
Data Index: 4795838 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.0944. Min Act: -0.1700
Data Index: 4795830 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4694. Min Range: -12.4694
Max Act: 11.0319. Min Act: -0.1700
Data Index: 6167354 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19