Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5679 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.5990. Min Act: -0.1700
Data Index: 608712 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.2552. Min Act: -0.1700
Data Index: 7512586 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.2552. Min Act: -0.1700
Data Index: 3328729 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.2240. Min Act: -0.1700
Data Index: 5226283 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.0677. Min Act: -0.1700
Data Index: 5138666 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.0365. Min Act: -0.1700
Data Index: 6452625 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.0677. Min Act: -0.1700
Data Index: 8704347 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.0365. Min Act: -0.1700
Data Index: 6086294 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.0052. Min Act: -0.1700
Data Index: 6693071 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.0052. Min Act: -0.1700
Data Index: 2818833 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.0052. Min Act: -0.1700
Data Index: 4779061 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.0052. Min Act: -0.1700
Data Index: 3244351 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.0052. Min Act: -0.1700
Data Index: 8711313 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5990. Min Range: -5.5990
Max Act: 5.0052. Min Act: -0.1700
Data Index: 5239095 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5990. Min Range: -5.5990
Max Act: 4.9427. Min Act: -0.1700
Data Index: 4077515 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5990. Min Range: -5.5990
Max Act: 4.9427. Min Act: -0.1700
Data Index: 2615687 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5990. Min Range: -5.5990
Max Act: 4.9740. Min Act: -0.1700
Data Index: 5291376 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5990. Min Range: -5.5990
Max Act: 4.9427. Min Act: -0.1700
Data Index: 3328725 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5990. Min Range: -5.5990
Max Act: 4.9427. Min Act: -0.1700
Data Index: 3998028 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5990. Min Range: -5.5990
Max Act: 4.9427. Min Act: -0.1700
Data Index: 5226282 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19