Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5518 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.4786. Min Act: -0.1700
Data Index: 5462726 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.4161. Min Act: -0.1700
Data Index: 4843140 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.4161. Min Act: -0.1700
Data Index: 5462727 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.3224. Min Act: -0.1700
Data Index: 1487504 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.3224. Min Act: -0.1700
Data Index: 6138929 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.2911. Min Act: -0.1700
Data Index: 3972725 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.2286. Min Act: -0.1700
Data Index: 8519345 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.1661. Min Act: -0.1700
Data Index: 3506093 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.1661. Min Act: -0.1700
Data Index: 8336280 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.1349. Min Act: -0.1700
Data Index: 2716725 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.1036. Min Act: -0.1700
Data Index: 2139024 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.1036. Min Act: -0.1700
Data Index: 113196 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.0724. Min Act: -0.1700
Data Index: 7192310 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.0411. Min Act: -0.1700
Data Index: 4159853 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.0411. Min Act: -0.1700
Data Index: 8280749 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.0411. Min Act: -0.1700
Data Index: 2736941 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.0099. Min Act: -0.1700
Data Index: 509353 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.0099. Min Act: -0.1700
Data Index: 7134623 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.0099. Min Act: -0.1700
Data Index: 7204727 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4786. Min Range: -7.4786
Max Act: 7.0411. Min Act: -0.1700
Data Index: 8156827 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19