Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3876 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.8318. Min Act: -0.1700
Data Index: 3815111 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.6443. Min Act: -0.1700
Data Index: 3370054 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.6756. Min Act: -0.1700
Data Index: 2429378 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.5193. Min Act: -0.1700
Data Index: 946481 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.4568. Min Act: -0.1700
Data Index: 1726257 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.4568. Min Act: -0.1700
Data Index: 8074397 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.4568. Min Act: -0.1700
Data Index: 6418576 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.4568. Min Act: -0.1700
Data Index: 6500585 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.4568. Min Act: -0.1700
Data Index: 1545047 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.4256. Min Act: -0.1700
Data Index: 2462574 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.4256. Min Act: -0.1700
Data Index: 1172650 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.4256. Min Act: -0.1700
Data Index: 5067551 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.4256. Min Act: -0.1700
Data Index: 6070236 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.3943. Min Act: -0.1700
Data Index: 6382001 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.3943. Min Act: -0.1700
Data Index: 3353844 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.3631. Min Act: -0.1700
Data Index: 7057113 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.3318. Min Act: -0.1700
Data Index: 8318620 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.3318. Min Act: -0.1700
Data Index: 5913178 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.3006. Min Act: -0.1700
Data Index: 4219183 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8318. Min Range: -5.8318
Max Act: 5.3318. Min Act: -0.1700
Data Index: 6010859 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19