Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3897 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2775. Min Range: -6.2775
Max Act: 6.2775. Min Act: -0.1700
Data Index: 205366 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2775. Min Range: -6.2775
Max Act: 6.2150. Min Act: -0.1700
Data Index: 8083203 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2775. Min Range: -6.2775
Max Act: 6.1212. Min Act: -0.1700
Data Index: 5409321 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2775. Min Range: -6.2775
Max Act: 6.0900. Min Act: -0.1700
Data Index: 3411041 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.9962. Min Act: -0.1700
Data Index: 6480982 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.9962. Min Act: -0.1700
Data Index: 6929404 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.9337. Min Act: -0.1700
Data Index: 6186901 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.9337. Min Act: -0.1700
Data Index: 575555 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.8712. Min Act: -0.1700
Data Index: 1662833 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.8400. Min Act: -0.1700
Data Index: 5527284 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.7775. Min Act: -0.1700
Data Index: 6704843 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.8087. Min Act: -0.1700
Data Index: 6661162 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.8087. Min Act: -0.1700
Data Index: 2261994 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.7775. Min Act: -0.1700
Data Index: 74129 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.7462. Min Act: -0.1700
Data Index: 5571943 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.7775. Min Act: -0.1700
Data Index: 135482 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.7775. Min Act: -0.1700
Data Index: 2770014 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.8087. Min Act: -0.1700
Data Index: 4878287 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.7462. Min Act: -0.1700
Data Index: 2329602 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2775. Min Range: -6.2775
Max Act: 5.7150. Min Act: -0.1700
Data Index: 7236438 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19