Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5521 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.9259. Min Act: -0.1700
Data Index: 3227823 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.8009. Min Act: -0.1700
Data Index: 5412451 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.7384. Min Act: -0.1700
Data Index: 8377740 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.7384. Min Act: -0.1700
Data Index: 4059154 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.6759. Min Act: -0.1700
Data Index: 1549870 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.6759. Min Act: -0.1700
Data Index: 678264 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.5822. Min Act: -0.1700
Data Index: 1930545 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.5822. Min Act: -0.1700
Data Index: 4318103 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.5197. Min Act: -0.1700
Data Index: 8377744 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.5509. Min Act: -0.1700
Data Index: 8609209 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.5197. Min Act: -0.1700
Data Index: 1029286 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.4884. Min Act: -0.1700
Data Index: 4929722 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.4884. Min Act: -0.1700
Data Index: 6807230 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.4884. Min Act: -0.1700
Data Index: 7968953 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.4884. Min Act: -0.1700
Data Index: 1930548 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.4572. Min Act: -0.1700
Data Index: 5739861 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.4572. Min Act: -0.1700
Data Index: 8174569 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.4259. Min Act: -0.1700
Data Index: 167911 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.4572. Min Act: -0.1700
Data Index: 2885073 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9259. Min Range: -5.9259
Max Act: 5.4572. Min Act: -0.1700
Data Index: 5692615 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19