Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5087 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0974. Min Range: -8.0974
Max Act: 8.0974. Min Act: -0.1700
Data Index: 8473651 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0974. Min Range: -8.0974
Max Act: 8.0661. Min Act: -0.1700
Data Index: 7466987 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.7849. Min Act: -0.1700
Data Index: 5014537 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.7536. Min Act: -0.1700
Data Index: 2572044 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.7536. Min Act: -0.1700
Data Index: 1027380 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.7536. Min Act: -0.1700
Data Index: 6652662 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.7224. Min Act: -0.1700
Data Index: 4752620 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.6911. Min Act: -0.1700
Data Index: 980585 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.6599. Min Act: -0.1700
Data Index: 761431 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.6911. Min Act: -0.1700
Data Index: 4226892 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.5974. Min Act: -0.1700
Data Index: 6580930 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.6286. Min Act: -0.1700
Data Index: 141694 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.5974. Min Act: -0.1700
Data Index: 5339034 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.6286. Min Act: -0.1700
Data Index: 3569396 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.6599. Min Act: -0.1700
Data Index: 1101919 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.5661. Min Act: -0.1700
Data Index: 3244273 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.5661. Min Act: -0.1700
Data Index: 3093869 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.5349. Min Act: -0.1700
Data Index: 2701875 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.5349. Min Act: -0.1700
Data Index: 3721197 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0974. Min Range: -8.0974
Max Act: 7.5661. Min Act: -0.1700
Data Index: 5222914 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19