Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2518. Min Range: -8.2518
Max Act: 8.2518. Min Act: -0.1700
Data Index: 5287471 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2518. Min Range: -8.2518
Max Act: 8.0018. Min Act: -0.1700
Data Index: 1249050 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.9393. Min Act: -0.1700
Data Index: 2498933 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2518. Min Range: -8.2518
Max Act: 8.0018. Min Act: -0.1700
Data Index: 4540311 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.9081. Min Act: -0.1700
Data Index: 7723389 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.9081. Min Act: -0.1700
Data Index: 2960013 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.9081. Min Act: -0.1700
Data Index: 5426125 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.9081. Min Act: -0.1700
Data Index: 5609109 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.8456. Min Act: -0.1700
Data Index: 4346483 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.8456. Min Act: -0.1700
Data Index: 482969 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.8768. Min Act: -0.1700
Data Index: 924560 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.8456. Min Act: -0.1700
Data Index: 3290744 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.8456. Min Act: -0.1700
Data Index: 8242604 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.8143. Min Act: -0.1700
Data Index: 2274208 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.8456. Min Act: -0.1700
Data Index: 7123791 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.8143. Min Act: -0.1700
Data Index: 855237 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.8143. Min Act: -0.1700
Data Index: 3652703 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.7831. Min Act: -0.1700
Data Index: 4679066 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.7831. Min Act: -0.1700
Data Index: 4716377 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2518. Min Range: -8.2518
Max Act: 7.7831. Min Act: -0.1700
Data Index: 7940698 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19