Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 778 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0495. Min Range: -3.0495
Max Act: 3.0495. Min Act: -0.1700
Data Index: 6566785 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0495. Min Range: -3.0495
Max Act: 3.0021. Min Act: -0.1700
Data Index: 5736285 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9705. Min Act: -0.1700
Data Index: 3959029 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9705. Min Act: -0.1700
Data Index: 5716138 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9547. Min Act: -0.1700
Data Index: 6350504 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9547. Min Act: -0.1700
Data Index: 1317138 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9547. Min Act: -0.1700
Data Index: 5991824 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9389. Min Act: -0.1700
Data Index: 7511444 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9389. Min Act: -0.1700
Data Index: 6580277 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9230. Min Act: -0.1700
Data Index: 4950107 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9389. Min Act: -0.1700
Data Index: 6428135 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9230. Min Act: -0.1700
Data Index: 7928159 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9072. Min Act: -0.1700
Data Index: 3008326 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9072. Min Act: -0.1700
Data Index: 2896314 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9072. Min Act: -0.1700
Data Index: 8331491 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.8754. Min Act: -0.1700
Data Index: 7127627 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9072. Min Act: -0.1700
Data Index: 6598968 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.8913. Min Act: -0.1700
Data Index: 4318016 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.8754. Min Act: -0.1700
Data Index: 4415038 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0495. Min Range: -3.0495
Max Act: 2.9072. Min Act: -0.1700
Data Index: 4999850 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19