Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4279 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1882. Min Range: -9.1882
Max Act: 9.1882. Min Act: -0.1700
Data Index: 3846867 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1882. Min Range: -9.1882
Max Act: 9.1882. Min Act: -0.1700
Data Index: 7753234 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.6257. Min Act: -0.1700
Data Index: 1350747 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.5632. Min Act: -0.1700
Data Index: 2765609 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.5632. Min Act: -0.1700
Data Index: 408315 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.5007. Min Act: -0.1700
Data Index: 6273871 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.4382. Min Act: -0.1700
Data Index: 5851191 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.3757. Min Act: -0.1700
Data Index: 3846866 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.3132. Min Act: -0.1700
Data Index: 1999910 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.2507. Min Act: -0.1700
Data Index: 5903733 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.2507. Min Act: -0.1700
Data Index: 3453574 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.2507. Min Act: -0.1700
Data Index: 6779377 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.2195. Min Act: -0.1700
Data Index: 3797914 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.2507. Min Act: -0.1700
Data Index: 7795067 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.1882. Min Act: -0.1700
Data Index: 3905090 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.1570. Min Act: -0.1700
Data Index: 7258272 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.1570. Min Act: -0.1700
Data Index: 7106074 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.1570. Min Act: -0.1700
Data Index: 5127493 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.1570. Min Act: -0.1700
Data Index: 7688436 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1882. Min Range: -9.1882
Max Act: 8.0945. Min Act: -0.1700
Data Index: 4526788 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19