Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3398. Min Range: -7.3398
Max Act: 7.3398. Min Act: -0.1700
Data Index: 3605567 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3398. Min Range: -7.3398
Max Act: 7.2461. Min Act: -0.1700
Data Index: 1350694 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.9961. Min Act: -0.1700
Data Index: 1035784 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.9648. Min Act: -0.1700
Data Index: 371424 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.9648. Min Act: -0.1700
Data Index: 3727938 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.9336. Min Act: -0.1700
Data Index: 3967325 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.8398. Min Act: -0.1700
Data Index: 5139352 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.8711. Min Act: -0.1700
Data Index: 371421 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.7773. Min Act: -0.1700
Data Index: 1561932 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.7461. Min Act: -0.1700
Data Index: 5139355 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.7148. Min Act: -0.1700
Data Index: 6813521 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.7148. Min Act: -0.1700
Data Index: 100384 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.7148. Min Act: -0.1700
Data Index: 4053872 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.6836. Min Act: -0.1700
Data Index: 691562 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.6836. Min Act: -0.1700
Data Index: 3605568 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.6523. Min Act: -0.1700
Data Index: 4518704 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.6836. Min Act: -0.1700
Data Index: 5101178 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.6211. Min Act: -0.1700
Data Index: 6276749 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.6211. Min Act: -0.1700
Data Index: 7086820 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3398. Min Range: -7.3398
Max Act: 6.6211. Min Act: -0.1700
Data Index: 1541868 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19