Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 819 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.8419. Min Act: -0.1700
Data Index: 8026833 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.7794. Min Act: -0.1700
Data Index: 3488793 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.7482. Min Act: -0.1700
Data Index: 8428282 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.7169. Min Act: -0.1700
Data Index: 2845183 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.5919. Min Act: -0.1700
Data Index: 3200688 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.5919. Min Act: -0.1700
Data Index: 4672791 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.5607. Min Act: -0.1700
Data Index: 3146989 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.5294. Min Act: -0.1700
Data Index: 7693144 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.5294. Min Act: -0.1700
Data Index: 5916891 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.5294. Min Act: -0.1700
Data Index: 5109379 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.5294. Min Act: -0.1700
Data Index: 3785384 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.5294. Min Act: -0.1700
Data Index: 7120283 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.5607. Min Act: -0.1700
Data Index: 236445 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.4982. Min Act: -0.1700
Data Index: 1073628 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.4982. Min Act: -0.1700
Data Index: 7770825 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.4982. Min Act: -0.1700
Data Index: 5108476 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.4982. Min Act: -0.1700
Data Index: 3892272 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.4669. Min Act: -0.1700
Data Index: 7502514 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.4669. Min Act: -0.1700
Data Index: 4053272 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8419. Min Range: -5.8419
Max Act: 5.4357. Min Act: -0.1700
Data Index: 5697100 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19