Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4136 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.6471. Min Act: -0.1700
Data Index: 5419473 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.6471. Min Act: -0.1700
Data Index: 744631 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.6471. Min Act: -0.1700
Data Index: 4119479 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.5846. Min Act: -0.1700
Data Index: 7819741 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.5221. Min Act: -0.1700
Data Index: 917178 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.4596. Min Act: -0.1700
Data Index: 5802647 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.4283. Min Act: -0.1700
Data Index: 7766070 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.4283. Min Act: -0.1700
Data Index: 3935358 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.3658. Min Act: -0.1700
Data Index: 2994448 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.3971. Min Act: -0.1700
Data Index: 2131070 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.3658. Min Act: -0.1700
Data Index: 146774 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.3658. Min Act: -0.1700
Data Index: 403947 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.3658. Min Act: -0.1700
Data Index: 5555794 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.3033. Min Act: -0.1700
Data Index: 4756681 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.3033. Min Act: -0.1700
Data Index: 919127 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.3346. Min Act: -0.1700
Data Index: 5465941 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.3033. Min Act: -0.1700
Data Index: 3405638 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.2408. Min Act: -0.1700
Data Index: 6482707 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.2721. Min Act: -0.1700
Data Index: 1963277 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6471. Min Range: -5.6471
Max Act: 5.2096. Min Act: -0.1700
Data Index: 3014576 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19