Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 343 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.7396. Min Act: -0.1700
Data Index: 2458853 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.6771. Min Act: -0.1700
Data Index: 6391649 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.5833. Min Act: -0.1700
Data Index: 989245 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.5521. Min Act: -0.1700
Data Index: 7723265 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.4583. Min Act: -0.1700
Data Index: 4542464 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.4271. Min Act: -0.1700
Data Index: 8561718 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.4271. Min Act: -0.1700
Data Index: 4784625 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.4271. Min Act: -0.1700
Data Index: 1725311 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.3958. Min Act: -0.1700
Data Index: 4302580 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.3958. Min Act: -0.1700
Data Index: 8319959 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.3646. Min Act: -0.1700
Data Index: 5808725 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.3333. Min Act: -0.1700
Data Index: 6812948 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.3333. Min Act: -0.1700
Data Index: 449115 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.3333. Min Act: -0.1700
Data Index: 5995141 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.2708. Min Act: -0.1700
Data Index: 3305587 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.3021. Min Act: -0.1700
Data Index: 1254408 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.2396. Min Act: -0.1700
Data Index: 289897 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.2396. Min Act: -0.1700
Data Index: 2548786 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.2083. Min Act: -0.1700
Data Index: 695128 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7396. Min Range: -7.7396
Max Act: 7.2396. Min Act: -0.1700
Data Index: 5018712 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19