Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3141 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.7165. Min Act: -0.1700
Data Index: 8796438 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.7165. Min Act: -0.1700
Data Index: 6228177 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.6852. Min Act: -0.1700
Data Index: 8133404 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.6540. Min Act: -0.1700
Data Index: 3642129 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.5915. Min Act: -0.1700
Data Index: 7498123 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4977. Min Act: -0.1700
Data Index: 850637 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.5290. Min Act: -0.1700
Data Index: 6205540 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4977. Min Act: -0.1700
Data Index: 196253 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4977. Min Act: -0.1700
Data Index: 6369713 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4977. Min Act: -0.1700
Data Index: 8439773 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4977. Min Act: -0.1700
Data Index: 7846847 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.5290. Min Act: -0.1700
Data Index: 5993053 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4977. Min Act: -0.1700
Data Index: 3193797 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4665. Min Act: -0.1700
Data Index: 4114041 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4977. Min Act: -0.1700
Data Index: 1113389 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4665. Min Act: -0.1700
Data Index: 3042570 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4352. Min Act: -0.1700
Data Index: 7861024 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4040. Min Act: -0.1700
Data Index: 3628541 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4040. Min Act: -0.1700
Data Index: 3356555 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7165. Min Range: -4.7165
Max Act: 4.4040. Min Act: -0.1700
Data Index: 4231948 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19