Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.7374. Min Act: -0.1700
Data Index: 6975490 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4562. Min Act: -0.1700
Data Index: 5167168 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4874. Min Act: -0.1700
Data Index: 4527763 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4874. Min Act: -0.1700
Data Index: 2926676 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4249. Min Act: -0.1700
Data Index: 1545569 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4249. Min Act: -0.1700
Data Index: 3894124 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.4249. Min Act: -0.1700
Data Index: 8232225 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3937. Min Act: -0.1700
Data Index: 3894126 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3624. Min Act: -0.1700
Data Index: 8149818 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3312. Min Act: -0.1700
Data Index: 4584468 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3624. Min Act: -0.1700
Data Index: 4412912 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3624. Min Act: -0.1700
Data Index: 7552617 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3624. Min Act: -0.1700
Data Index: 7803589 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3624. Min Act: -0.1700
Data Index: 3327785 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3624. Min Act: -0.1699
Data Index: 7307374 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3312. Min Act: -0.1700
Data Index: 2216212 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3312. Min Act: -0.1700
Data Index: 4636648 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3312. Min Act: -0.1700
Data Index: 3036153 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3312. Min Act: -0.1700
Data Index: 4848624 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7374. Min Range: -5.7374
Max Act: 5.3312. Min Act: -0.1700
Data Index: 1355975 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19