Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3347 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.4575. Min Range: -14.4575
Max Act: 14.4575. Min Act: -0.1700
Data Index: 3999407 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.4575. Min Range: -14.4575
Max Act: 14.4575. Min Act: -0.1700
Data Index: 2344470 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.4575. Min Range: -14.4575
Max Act: 14.3325. Min Act: -0.1700
Data Index: 2616187 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.4575. Min Range: -14.4575
Max Act: 14.2700. Min Act: -0.1700
Data Index: 1173998 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.4575. Min Range: -14.4575
Max Act: 14.1450. Min Act: -0.1700
Data Index: 6145053 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.4575. Min Range: -14.4575
Max Act: 14.0825. Min Act: -0.1700
Data Index: 1745123 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.4575. Min Range: -14.4575
Max Act: 14.0825. Min Act: -0.1700
Data Index: 5229989 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.4575. Min Range: -14.4575
Max Act: 14.0200. Min Act: -0.1700
Data Index: 7730947 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.4575. Min Range: -14.4575
Max Act: 14.0825. Min Act: -0.1700
Data Index: 7244133 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.4575. Min Range: -14.4575
Max Act: 13.9575. Min Act: -0.1700
Data Index: 6841494 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.4575. Min Range: -14.4575
Max Act: 13.8950. Min Act: -0.1700
Data Index: 8169905 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.4575. Min Range: -14.4575
Max Act: 13.9575. Min Act: -0.1700
Data Index: 6121314 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.4575. Min Range: -14.4575
Max Act: 13.8325. Min Act: -0.1700
Data Index: 3963989 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.4575. Min Range: -14.4575
Max Act: 13.8325. Min Act: -0.1700
Data Index: 2293203 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.4575. Min Range: -14.4575
Max Act: 13.8325. Min Act: -0.1700
Data Index: 3814459 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.4575. Min Range: -14.4575
Max Act: 13.7700. Min Act: -0.1700
Data Index: 6399361 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.4575. Min Range: -14.4575
Max Act: 13.7700. Min Act: -0.1700
Data Index: 2690118 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.4575. Min Range: -14.4575
Max Act: 13.7075. Min Act: -0.1700
Data Index: 7078204 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.4575. Min Range: -14.4575
Max Act: 13.7075. Min Act: -0.1700
Data Index: 8322872 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.4575. Min Range: -14.4575
Max Act: 13.7075. Min Act: -0.1700
Data Index: 3099227 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19