Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1946 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.3299. Min Act: -0.1700
Data Index: 6472928 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.3299. Min Act: -0.1700
Data Index: 7790782 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.3299. Min Act: -0.1700
Data Index: 7123824 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.2987. Min Act: -0.1700
Data Index: 263970 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.2987. Min Act: -0.1700
Data Index: 4741433 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.2987. Min Act: -0.1700
Data Index: 7562531 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.2049. Min Act: -0.1700
Data Index: 317465 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.2362. Min Act: -0.1700
Data Index: 4991684 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.2362. Min Act: -0.1700
Data Index: 1428750 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.2049. Min Act: -0.1700
Data Index: 7550327 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.1737. Min Act: -0.1700
Data Index: 3362013 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.1737. Min Act: -0.1700
Data Index: 2753171 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.2049. Min Act: -0.1700
Data Index: 3533248 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.2049. Min Act: -0.1700
Data Index: 5390557 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.1737. Min Act: -0.1700
Data Index: 3641515 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.2049. Min Act: -0.1700
Data Index: 4491662 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.1737. Min Act: -0.1700
Data Index: 6713885 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.1112. Min Act: -0.1700
Data Index: 7134706 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.1424. Min Act: -0.1700
Data Index: 4903490 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.1112. Min Act: -0.1700
Data Index: 6648783 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19