Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5157 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5677. Min Range: -6.5677
Max Act: 6.5677. Min Act: -0.1700
Data Index: 2708432 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5677. Min Range: -6.5677
Max Act: 6.4739. Min Act: -0.1700
Data Index: 121641 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5677. Min Range: -6.5677
Max Act: 6.3802. Min Act: -0.1700
Data Index: 6470042 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5677. Min Range: -6.5677
Max Act: 6.2239. Min Act: -0.1700
Data Index: 7857284 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5677. Min Range: -6.5677
Max Act: 6.1614. Min Act: -0.1700
Data Index: 3734022 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5677. Min Range: -6.5677
Max Act: 6.1302. Min Act: -0.1700
Data Index: 8796027 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5677. Min Range: -6.5677
Max Act: 6.0989. Min Act: -0.1700
Data Index: 2308572 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5677. Min Range: -6.5677
Max Act: 6.0677. Min Act: -0.1700
Data Index: 574211 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5677. Min Range: -6.5677
Max Act: 6.0364. Min Act: -0.1700
Data Index: 1972819 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5677. Min Range: -6.5677
Max Act: 6.0052. Min Act: -0.1700
Data Index: 7423569 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5677. Min Range: -6.5677
Max Act: 6.0052. Min Act: -0.1700
Data Index: 8603410 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5677. Min Range: -6.5677
Max Act: 6.0052. Min Act: -0.1700
Data Index: 4343980 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5677. Min Range: -6.5677
Max Act: 5.9427. Min Act: -0.1700
Data Index: 6088323 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5677. Min Range: -6.5677
Max Act: 5.9427. Min Act: -0.1700
Data Index: 3734021 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5677. Min Range: -6.5677
Max Act: 5.9114. Min Act: -0.1700
Data Index: 7621931 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5677. Min Range: -6.5677
Max Act: 5.9114. Min Act: -0.1700
Data Index: 2044346 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5677. Min Range: -6.5677
Max Act: 5.8802. Min Act: -0.1700
Data Index: 5193943 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5677. Min Range: -6.5677
Max Act: 5.8802. Min Act: -0.1700
Data Index: 6011623 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5677. Min Range: -6.5677
Max Act: 5.8489. Min Act: -0.1700
Data Index: 5096156 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5677. Min Range: -6.5677
Max Act: 5.8802. Min Act: -0.1700
Data Index: 4318839 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19