Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4272. Min Range: -6.4272
Max Act: 6.4272. Min Act: -0.1700
Data Index: 2350409 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4272. Min Range: -6.4272
Max Act: 6.4272. Min Act: -0.1700
Data Index: 1825631 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4272. Min Range: -6.4272
Max Act: 6.3335. Min Act: -0.1700
Data Index: 1432767 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4272. Min Range: -6.4272
Max Act: 6.2397. Min Act: -0.1700
Data Index: 4837836 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4272. Min Range: -6.4272
Max Act: 6.1147. Min Act: -0.1700
Data Index: 6507174 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4272. Min Range: -6.4272
Max Act: 6.0522. Min Act: -0.1700
Data Index: 5618298 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.9272. Min Act: -0.1700
Data Index: 3368738 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.9272. Min Act: -0.1700
Data Index: 2703920 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.8960. Min Act: -0.1700
Data Index: 1645460 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.8960. Min Act: -0.1700
Data Index: 2444425 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.9272. Min Act: -0.1700
Data Index: 398852 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.8647. Min Act: -0.1700
Data Index: 2063905 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.8647. Min Act: -0.1700
Data Index: 7561831 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.8647. Min Act: -0.1700
Data Index: 1443359 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.8335. Min Act: -0.1700
Data Index: 7376884 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.8022. Min Act: -0.1700
Data Index: 7219433 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.8022. Min Act: -0.1700
Data Index: 4473055 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.8022. Min Act: -0.1700
Data Index: 7972333 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.7710. Min Act: -0.1700
Data Index: 4793060 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4272. Min Range: -6.4272
Max Act: 5.7397. Min Act: -0.1700
Data Index: 3437012 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19