Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1703 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.7554. Min Act: -0.1700
Data Index: 2795000 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6304. Min Act: -0.1700
Data Index: 3245583 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6304. Min Act: -0.1700
Data Index: 4230707 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.5992. Min Act: -0.1700
Data Index: 6966478 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.5679. Min Act: -0.1700
Data Index: 5703623 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.5679. Min Act: -0.1700
Data Index: 7170255 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.5679. Min Act: -0.1700
Data Index: 4255900 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.4742. Min Act: -0.1700
Data Index: 967276 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.4429. Min Act: -0.1700
Data Index: 8760229 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.4429. Min Act: -0.1700
Data Index: 5858820 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.4429. Min Act: -0.1700
Data Index: 3074339 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.3804. Min Act: -0.1700
Data Index: 1084654 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.3804. Min Act: -0.1700
Data Index: 7067524 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.3804. Min Act: -0.1700
Data Index: 7090872 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.3804. Min Act: -0.1700
Data Index: 201843 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.3492. Min Act: -0.1700
Data Index: 2908151 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.3179. Min Act: -0.1700
Data Index: 4459058 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.3179. Min Act: -0.1700
Data Index: 1654921 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.3492. Min Act: -0.1700
Data Index: 851920 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.3492. Min Act: -0.1700
Data Index: 8623118 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19