Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1152. Min Range: -7.1152
Max Act: 7.1152. Min Act: -0.1700
Data Index: 4175743 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.9590. Min Act: -0.1700
Data Index: 4162189 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.8965. Min Act: -0.1700
Data Index: 8273012 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.7090. Min Act: -0.1700
Data Index: 2448160 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.6777. Min Act: -0.1700
Data Index: 5224134 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.6777. Min Act: -0.1700
Data Index: 2738821 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.6777. Min Act: -0.1700
Data Index: 8405095 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.5527. Min Act: -0.1700
Data Index: 4039521 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.5527. Min Act: -0.1700
Data Index: 4716919 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.5215. Min Act: -0.1700
Data Index: 5081151 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.5215. Min Act: -0.1700
Data Index: 4914368 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.5215. Min Act: -0.1700
Data Index: 5421920 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.5215. Min Act: -0.1700
Data Index: 7544937 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.5215. Min Act: -0.1700
Data Index: 341852 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.4902. Min Act: -0.1700
Data Index: 5178557 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.4902. Min Act: -0.1700
Data Index: 5002623 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.4590. Min Act: -0.1700
Data Index: 6662337 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.4902. Min Act: -0.1700
Data Index: 2432250 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.4277. Min Act: -0.1700
Data Index: 6621073 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1152. Min Range: -7.1152
Max Act: 6.4902. Min Act: -0.1700
Data Index: 5178558 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19