Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0054. Min Range: -9.0054
Max Act: 9.0054. Min Act: -0.1700
Data Index: 5738020 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.8804. Min Act: -0.1700
Data Index: 8131805 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.8804. Min Act: -0.1700
Data Index: 4409921 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.7554. Min Act: -0.1700
Data Index: 4352881 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.6304. Min Act: -0.1700
Data Index: 6963482 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.6304. Min Act: -0.1700
Data Index: 1355024 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.5679. Min Act: -0.1700
Data Index: 5547322 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.5054. Min Act: -0.1700
Data Index: 7701063 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.5679. Min Act: -0.1700
Data Index: 6047538 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.5054. Min Act: -0.1700
Data Index: 8679904 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.5054. Min Act: -0.1700
Data Index: 1289796 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.4429. Min Act: -0.1700
Data Index: 1494382 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.4429. Min Act: -0.1700
Data Index: 2485442 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.4429. Min Act: -0.1700
Data Index: 4092921 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.3804. Min Act: -0.1700
Data Index: 8809255 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.3804. Min Act: -0.1700
Data Index: 5383537 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.3804. Min Act: -0.1700
Data Index: 5940527 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.3179. Min Act: -0.1700
Data Index: 7992474 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.3179. Min Act: -0.1700
Data Index: 3247947 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0054. Min Range: -9.0054
Max Act: 8.3179. Min Act: -0.1700
Data Index: 4536128 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19