Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.5621. Min Act: -0.1700
Data Index: 8313259 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.4059. Min Act: -0.1700
Data Index: 1383409 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.2809. Min Act: -0.1700
Data Index: 1169871 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.2184. Min Act: -0.1700
Data Index: 2556952 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1871. Min Act: -0.1700
Data Index: 1029135 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1871. Min Act: -0.1700
Data Index: 3352470 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1246. Min Act: -0.1700
Data Index: 6052500 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1559. Min Act: -0.1700
Data Index: 6575593 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1246. Min Act: -0.1700
Data Index: 1098816 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1246. Min Act: -0.1700
Data Index: 7222922 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.0934. Min Act: -0.1700
Data Index: 7139442 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1559. Min Act: -0.1700
Data Index: 8734433 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.0934. Min Act: -0.1700
Data Index: 4535026 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.0934. Min Act: -0.1700
Data Index: 2885104 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.0934. Min Act: -0.1700
Data Index: 5044790 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.0934. Min Act: -0.1700
Data Index: 6712053 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.0934. Min Act: -0.1699
Data Index: 3632065 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.0934. Min Act: -0.1700
Data Index: 5287117 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.0621. Min Act: -0.1700
Data Index: 1252514 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.0621. Min Act: -0.1700
Data Index: 7387240 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19