Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1042 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3153. Min Range: -3.3153
Max Act: 3.3153. Min Act: -0.1700
Data Index: 5402523 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3153. Min Range: -3.3153
Max Act: 3.1267. Min Act: -0.1700
Data Index: 5607889 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3153. Min Range: -3.3153
Max Act: 3.1267. Min Act: -0.1700
Data Index: 3209262 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3153. Min Range: -3.3153
Max Act: 3.0952. Min Act: -0.1700
Data Index: 6237522 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3153. Min Range: -3.3153
Max Act: 3.0794. Min Act: -0.1700
Data Index: 8422783 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3153. Min Range: -3.3153
Max Act: 3.0479. Min Act: -0.1700
Data Index: 5176834 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3153. Min Range: -3.3153
Max Act: 3.0005. Min Act: -0.1700
Data Index: 2758266 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3153. Min Range: -3.3153
Max Act: 3.0163. Min Act: -0.1700
Data Index: 3001868 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3153. Min Range: -3.3153
Max Act: 3.0005. Min Act: -0.1700
Data Index: 1916113 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3153. Min Range: -3.3153
Max Act: 2.9847. Min Act: -0.1700
Data Index: 1700088 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3153. Min Range: -3.3153
Max Act: 2.9847. Min Act: -0.1700
Data Index: 2432913 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3153. Min Range: -3.3153
Max Act: 2.9847. Min Act: -0.1700
Data Index: 6607951 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3153. Min Range: -3.3153
Max Act: 2.9372. Min Act: -0.1700
Data Index: 4944956 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3153. Min Range: -3.3153
Max Act: 2.8896. Min Act: -0.1700
Data Index: 6564019 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3153. Min Range: -3.3153
Max Act: 2.8896. Min Act: -0.1700
Data Index: 2283024 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3153. Min Range: -3.3153
Max Act: 2.8896. Min Act: -0.1700
Data Index: 923621 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3153. Min Range: -3.3153
Max Act: 2.8896. Min Act: -0.1700
Data Index: 6345344 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3153. Min Range: -3.3153
Max Act: 2.8896. Min Act: -0.1700
Data Index: 3137898 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3153. Min Range: -3.3153
Max Act: 2.8579. Min Act: -0.1700
Data Index: 1676252 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3153. Min Range: -3.3153
Max Act: 2.8738. Min Act: -0.1700
Data Index: 203576 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19