Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3855 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.7210. Min Act: -0.1700
Data Index: 6573771 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.6585. Min Act: -0.1700
Data Index: 8221559 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.6272. Min Act: -0.1700
Data Index: 4004788 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.6272. Min Act: -0.1700
Data Index: 4029003 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.5960. Min Act: -0.1700
Data Index: 6433560 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.5335. Min Act: -0.1700
Data Index: 426603 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.5022. Min Act: -0.1700
Data Index: 2394855 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.5647. Min Act: -0.1700
Data Index: 3515714 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.5022. Min Act: -0.1700
Data Index: 6680324 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.5022. Min Act: -0.1700
Data Index: 5790419 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.5022. Min Act: -0.1700
Data Index: 962803 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.4710. Min Act: -0.1700
Data Index: 4297683 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.4710. Min Act: -0.1700
Data Index: 6445337 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.4397. Min Act: -0.1700
Data Index: 2470684 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.4710. Min Act: -0.1700
Data Index: 8533311 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.4397. Min Act: -0.1700
Data Index: 265812 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.4397. Min Act: -0.1700
Data Index: 1762330 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.4397. Min Act: -0.1700
Data Index: 792089 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.4085. Min Act: -0.1700
Data Index: 3933823 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7210. Min Range: -5.7210
Max Act: 5.4085. Min Act: -0.1700
Data Index: 5615008 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19