Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2538 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.7436. Min Act: -0.1700
Data Index: 8175216 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.5561. Min Act: -0.1700
Data Index: 3373316 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.4936. Min Act: -0.1700
Data Index: 8040721 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.3374. Min Act: -0.1700
Data Index: 8549134 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.3374. Min Act: -0.1700
Data Index: 969249 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.3061. Min Act: -0.1700
Data Index: 8537001 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.2749. Min Act: -0.1700
Data Index: 2823767 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.2749. Min Act: -0.1700
Data Index: 4518135 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.2436. Min Act: -0.1700
Data Index: 3286813 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.2124. Min Act: -0.1700
Data Index: 8721369 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.2124. Min Act: -0.1700
Data Index: 5785583 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.1811. Min Act: -0.1700
Data Index: 6786465 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.1499. Min Act: -0.1700
Data Index: 2276405 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.1499. Min Act: -0.1700
Data Index: 6185366 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.1499. Min Act: -0.1700
Data Index: 744979 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.1186. Min Act: -0.1700
Data Index: 203172 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.1186. Min Act: -0.1700
Data Index: 6124126 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.1186. Min Act: -0.1700
Data Index: 4020446 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.0561. Min Act: -0.1700
Data Index: 1019671 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7436. Min Range: -7.7436
Max Act: 7.0561. Min Act: -0.1700
Data Index: 8299061 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19