Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1175. Min Range: -6.1175
Max Act: 6.1175. Min Act: -0.1700
Data Index: 2097994 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1175. Min Range: -6.1175
Max Act: 6.0862. Min Act: -0.1700
Data Index: 5305616 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1175. Min Range: -6.1175
Max Act: 6.0237. Min Act: -0.1700
Data Index: 5519761 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.9300. Min Act: -0.1700
Data Index: 921937 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.8987. Min Act: -0.1700
Data Index: 8359728 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.8675. Min Act: -0.1700
Data Index: 7383533 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.7737. Min Act: -0.1700
Data Index: 2226069 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.7737. Min Act: -0.1700
Data Index: 7836755 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.7425. Min Act: -0.1700
Data Index: 3896530 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.7112. Min Act: -0.1700
Data Index: 8214079 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.6487. Min Act: -0.1700
Data Index: 740133 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.6175. Min Act: -0.1700
Data Index: 3687888 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.6487. Min Act: -0.1700
Data Index: 4233397 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.6487. Min Act: -0.1700
Data Index: 2270288 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.6175. Min Act: -0.1700
Data Index: 4121601 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.5862. Min Act: -0.1700
Data Index: 5120496 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.5862. Min Act: -0.1700
Data Index: 1172035 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.5237. Min Act: -0.1700
Data Index: 6025215 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.5550. Min Act: -0.1700
Data Index: 6006353 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1175. Min Range: -6.1175
Max Act: 5.5550. Min Act: -0.1700
Data Index: 4709352 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19