Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.6848. Min Act: -0.1700
Data Index: 7645115 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.4973. Min Act: -0.1700
Data Index: 987639 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.4036. Min Act: -0.1700
Data Index: 6660234 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.3723. Min Act: -0.1700
Data Index: 8706749 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.3411. Min Act: -0.1700
Data Index: 1609567 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2786. Min Act: -0.1700
Data Index: 6458337 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2786. Min Act: -0.1700
Data Index: 6284281 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2473. Min Act: -0.1700
Data Index: 664609 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2473. Min Act: -0.1700
Data Index: 3095218 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2473. Min Act: -0.1700
Data Index: 3683946 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.2473. Min Act: -0.1700
Data Index: 4272075 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.1848. Min Act: -0.1700
Data Index: 5156175 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.1848. Min Act: -0.1700
Data Index: 5649787 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.1536. Min Act: -0.1700
Data Index: 2607297 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.1536. Min Act: -0.1700
Data Index: 7876159 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.1536. Min Act: -0.1700
Data Index: 5667118 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.1223. Min Act: -0.1700
Data Index: 372540 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.1223. Min Act: -0.1700
Data Index: 4127712 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.0598. Min Act: -0.1700
Data Index: 8439355 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6848. Min Range: -5.6848
Max Act: 5.0911. Min Act: -0.1700
Data Index: 1578474 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19