Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 846 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.4277. Min Act: -0.1700
Data Index: 6351380 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.3965. Min Act: -0.1700
Data Index: 1597394 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.3965. Min Act: -0.1700
Data Index: 1597380 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.3965. Min Act: -0.1700
Data Index: 6351392 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.3965. Min Act: -0.1700
Data Index: 1495208 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.3652. Min Act: -0.1700
Data Index: 1589474 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.3652. Min Act: -0.1700
Data Index: 1589491 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.3652. Min Act: -0.1700
Data Index: 3449304 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.3340. Min Act: -0.1700
Data Index: 1495194 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.3340. Min Act: -0.1700
Data Index: 4776114 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.2715. Min Act: -0.1700
Data Index: 8070616 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.3027. Min Act: -0.1700
Data Index: 5704795 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.3027. Min Act: -0.1700
Data Index: 5704816 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.2089. Min Act: -0.1700
Data Index: 3588215 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.2089. Min Act: -0.1700
Data Index: 1806249 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.1464. Min Act: -0.1700
Data Index: 1443524 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.1464. Min Act: -0.1700
Data Index: 4935568 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.1152. Min Act: -0.1700
Data Index: 5443586 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.1152. Min Act: -0.1700
Data Index: 7458282 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4277. Min Range: -4.4277
Max Act: 4.0839. Min Act: -0.1700
Data Index: 4935273 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19