Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.8178. Min Act: -0.1700
Data Index: 5045342 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.7241. Min Act: -0.1700
Data Index: 129024 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.7553. Min Act: -0.1700
Data Index: 4061614 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.7241. Min Act: -0.1700
Data Index: 196481 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.6928. Min Act: -0.1700
Data Index: 5119695 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.5991. Min Act: -0.1700
Data Index: 3574391 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.5053. Min Act: -0.1700
Data Index: 1908577 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.5053. Min Act: -0.1700
Data Index: 8373695 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.5053. Min Act: -0.1700
Data Index: 6067154 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.4741. Min Act: -0.1700
Data Index: 5019257 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.4428. Min Act: -0.1700
Data Index: 4986959 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.4116. Min Act: -0.1700
Data Index: 5444206 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.4116. Min Act: -0.1700
Data Index: 6233284 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.3803. Min Act: -0.1700
Data Index: 2573268 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.4116. Min Act: -0.1700
Data Index: 152798 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.3803. Min Act: -0.1700
Data Index: 3764895 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.3803. Min Act: -0.1700
Data Index: 4461246 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.3803. Min Act: -0.1700
Data Index: 415539 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.3491. Min Act: -0.1700
Data Index: 2752570 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8178. Min Range: -5.8178
Max Act: 5.3491. Min Act: -0.1700
Data Index: 1733268 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19