Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4911 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.9061. Min Act: -0.1700
Data Index: 7491074 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.8436. Min Act: -0.1700
Data Index: 7602211 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.8124. Min Act: -0.1700
Data Index: 5072423 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.7186. Min Act: -0.1700
Data Index: 4034307 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.6561. Min Act: -0.1700
Data Index: 703053 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.6561. Min Act: -0.1700
Data Index: 8799078 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.5311. Min Act: -0.1700
Data Index: 6575268 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.4999. Min Act: -0.1700
Data Index: 5752020 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.5311. Min Act: -0.1700
Data Index: 2382991 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.5311. Min Act: -0.1700
Data Index: 729916 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.4999. Min Act: -0.1700
Data Index: 7897123 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.4686. Min Act: -0.1700
Data Index: 4910668 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.4686. Min Act: -0.1700
Data Index: 6275551 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.4374. Min Act: -0.1700
Data Index: 364349 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.4686. Min Act: -0.1700
Data Index: 4708140 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.4061. Min Act: -0.1700
Data Index: 7221358 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.4061. Min Act: -0.1700
Data Index: 2520607 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.3749. Min Act: -0.1700
Data Index: 2897056 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.3749. Min Act: -0.1700
Data Index: 6212275 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9061. Min Range: -6.9061
Max Act: 6.3749. Min Act: -0.1700
Data Index: 3800040 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19