Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5576 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.9967. Min Act: -0.1700
Data Index: 772168 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.8717. Min Act: -0.1700
Data Index: 355607 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.8404. Min Act: -0.1700
Data Index: 536779 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.7779. Min Act: -0.1700
Data Index: 7344451 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.7467. Min Act: -0.1700
Data Index: 2343091 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.7467. Min Act: -0.1700
Data Index: 6024681 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.6842. Min Act: -0.1700
Data Index: 6137454 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.6842. Min Act: -0.1700
Data Index: 5994259 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.7154. Min Act: -0.1700
Data Index: 5994266 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.6529. Min Act: -0.1700
Data Index: 1038591 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.6529. Min Act: -0.1700
Data Index: 5994270 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.6529. Min Act: -0.1700
Data Index: 5994263 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.6529. Min Act: -0.1700
Data Index: 5994267 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.6529. Min Act: -0.1700
Data Index: 4107555 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.6217. Min Act: -0.1700
Data Index: 3946146 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.6217. Min Act: -0.1700
Data Index: 5994255 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.6217. Min Act: -0.1700
Data Index: 5994268 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.5904. Min Act: -0.1700
Data Index: 1283867 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.5904. Min Act: -0.1700
Data Index: 4016902 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9967. Min Range: -5.9967
Max Act: 5.5904. Min Act: -0.1700
Data Index: 5994262 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19