Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4226. Min Range: -6.4226
Max Act: 6.4226. Min Act: -0.1700
Data Index: 6003421 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4226. Min Range: -6.4226
Max Act: 6.2038. Min Act: -0.1700
Data Index: 6097639 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4226. Min Range: -6.4226
Max Act: 6.0788. Min Act: -0.1700
Data Index: 4276233 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.8288. Min Act: -0.1700
Data Index: 4484128 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.8288. Min Act: -0.1700
Data Index: 4507029 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.8288. Min Act: -0.1700
Data Index: 8723484 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.7976. Min Act: -0.1700
Data Index: 6331371 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.7663. Min Act: -0.1700
Data Index: 3160339 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.7663. Min Act: -0.1700
Data Index: 7952705 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.7351. Min Act: -0.1700
Data Index: 1129029 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.7038. Min Act: -0.1700
Data Index: 7001259 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.7351. Min Act: -0.1700
Data Index: 6867495 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.7038. Min Act: -0.1700
Data Index: 3540366 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.7038. Min Act: -0.1700
Data Index: 6890280 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.6726. Min Act: -0.1700
Data Index: 3990076 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.6726. Min Act: -0.1700
Data Index: 6524022 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.6726. Min Act: -0.1700
Data Index: 4219665 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.6726. Min Act: -0.1700
Data Index: 8633368 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.6413. Min Act: -0.1700
Data Index: 8027579 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4226. Min Range: -6.4226
Max Act: 5.6726. Min Act: -0.1700
Data Index: 380115 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19