Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 923 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.9878. Min Act: -0.1700
Data Index: 4412556 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.9253. Min Act: -0.1700
Data Index: 3407222 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.8003. Min Act: -0.1700
Data Index: 8250387 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.7378. Min Act: -0.1700
Data Index: 7204836 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.7378. Min Act: -0.1700
Data Index: 4981601 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.7378. Min Act: -0.1700
Data Index: 3067021 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.6753. Min Act: -0.1700
Data Index: 754654 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.6128. Min Act: -0.1700
Data Index: 7383198 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.6128. Min Act: -0.1700
Data Index: 8795896 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.4878. Min Act: -0.1700
Data Index: 7136405 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.4878. Min Act: -0.1700
Data Index: 1123873 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.4253. Min Act: -0.1700
Data Index: 7532420 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.4253. Min Act: -0.1700
Data Index: 6092727 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.4253. Min Act: -0.1700
Data Index: 129614 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.3628. Min Act: -0.1700
Data Index: 8467318 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.3628. Min Act: -0.1700
Data Index: 4285333 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.3628. Min Act: -0.1700
Data Index: 371429 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.3628. Min Act: -0.1700
Data Index: 230714 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.3003. Min Act: -0.1700
Data Index: 3815208 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9878. Min Range: -9.9878
Max Act: 9.3003. Min Act: -0.1700
Data Index: 8469817 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19