Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.7464. Min Act: -0.1700
Data Index: 7131749 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.7151. Min Act: -0.1700
Data Index: 8469717 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.6526. Min Act: -0.1700
Data Index: 2230269 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5900. Min Act: -0.1700
Data Index: 3455664 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.6056. Min Act: -0.1700
Data Index: 5051062 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.6056. Min Act: -0.1700
Data Index: 5226175 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.6056. Min Act: -0.1700
Data Index: 24695 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5743. Min Act: -0.1700
Data Index: 3778412 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5743. Min Act: -0.1700
Data Index: 7697529 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5587. Min Act: -0.1700
Data Index: 2343582 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5587. Min Act: -0.1700
Data Index: 6749966 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5587. Min Act: -0.1700
Data Index: 6460244 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5273. Min Act: -0.1700
Data Index: 8115855 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5587. Min Act: -0.1700
Data Index: 3051559 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5273. Min Act: -0.1700
Data Index: 1488332 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5430. Min Act: -0.1700
Data Index: 8189157 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5430. Min Act: -0.1700
Data Index: 4869365 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5430. Min Act: -0.1700
Data Index: 3258604 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5430. Min Act: -0.1700
Data Index: 3276214 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7464. Min Range: -3.7464
Max Act: 3.5430. Min Act: -0.1700
Data Index: 485203 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19