Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4358 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.5339. Min Act: -0.1700
Data Index: 2424737 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.5026. Min Act: -0.1700
Data Index: 3315501 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.4401. Min Act: -0.1700
Data Index: 5681700 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.4089. Min Act: -0.1700
Data Index: 4875121 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.3464. Min Act: -0.1700
Data Index: 3211021 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.3151. Min Act: -0.1700
Data Index: 5625867 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.2839. Min Act: -0.1700
Data Index: 3398836 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.2839. Min Act: -0.1700
Data Index: 2014146 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.2839. Min Act: -0.1700
Data Index: 5625866 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.2526. Min Act: -0.1700
Data Index: 604387 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.2526. Min Act: -0.1700
Data Index: 8463430 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.2526. Min Act: -0.1700
Data Index: 2074380 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.1901. Min Act: -0.1700
Data Index: 2424739 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.2214. Min Act: -0.1700
Data Index: 3980445 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.2214. Min Act: -0.1700
Data Index: 922280 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.2214. Min Act: -0.1700
Data Index: 922282 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.2214. Min Act: -0.1700
Data Index: 620516 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.1901. Min Act: -0.1700
Data Index: 8717991 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.2214. Min Act: -0.1700
Data Index: 2074384 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5339. Min Range: -5.5339
Max Act: 5.1901. Min Act: -0.1700
Data Index: 5625862 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19