Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4193 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1460. Min Range: -9.1460
Max Act: 9.1460. Min Act: -0.1700
Data Index: 6239729 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.8960. Min Act: -0.1700
Data Index: 5650012 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.8335. Min Act: -0.1700
Data Index: 6128559 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.8335. Min Act: -0.1700
Data Index: 7622507 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.8960. Min Act: -0.1700
Data Index: 4783459 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.8335. Min Act: -0.1700
Data Index: 317649 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.8335. Min Act: -0.1700
Data Index: 694642 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.7710. Min Act: -0.1700
Data Index: 7639286 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.7710. Min Act: -0.1700
Data Index: 5479386 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.7710. Min Act: -0.1700
Data Index: 2223887 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.7085. Min Act: -0.1700
Data Index: 6389081 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.7085. Min Act: -0.1700
Data Index: 5018082 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.7085. Min Act: -0.1700
Data Index: 5499282 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.6460. Min Act: -0.1700
Data Index: 66580 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.7085. Min Act: -0.1700
Data Index: 7174826 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.5835. Min Act: -0.1700
Data Index: 7292118 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.6460. Min Act: -0.1700
Data Index: 7372566 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.7085. Min Act: -0.1700
Data Index: 2758808 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.6460. Min Act: -0.1700
Data Index: 2333429 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1460. Min Range: -9.1460
Max Act: 8.6460. Min Act: -0.1700
Data Index: 55921 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19