Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1425. Min Range: -7.1425
Max Act: 7.1425. Min Act: -0.1700
Data Index: 1859392 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.6737. Min Act: -0.1700
Data Index: 5543609 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.6425. Min Act: -0.1700
Data Index: 3304412 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.6112. Min Act: -0.1700
Data Index: 3287823 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.6112. Min Act: -0.1700
Data Index: 5100654 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.4862. Min Act: -0.1700
Data Index: 8406642 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.4862. Min Act: -0.1700
Data Index: 4969713 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.4550. Min Act: -0.1700
Data Index: 4261215 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.4550. Min Act: -0.1700
Data Index: 4202667 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.4237. Min Act: -0.1700
Data Index: 5537629 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.4550. Min Act: -0.1700
Data Index: 223255 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.3925. Min Act: -0.1700
Data Index: 4466708 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.3925. Min Act: -0.1700
Data Index: 7735600 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.3300. Min Act: -0.1700
Data Index: 8114771 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.2987. Min Act: -0.1700
Data Index: 1911721 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.2987. Min Act: -0.1700
Data Index: 3947097 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.2987. Min Act: -0.1700
Data Index: 177897 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.2987. Min Act: -0.1700
Data Index: 5253935 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.2987. Min Act: -0.1700
Data Index: 3420108 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1425. Min Range: -7.1425
Max Act: 6.2987. Min Act: -0.1700
Data Index: 1301925 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19