Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.8796. Min Act: -0.1700
Data Index: 2485090 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.6921. Min Act: -0.1700
Data Index: 1195886 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.7234. Min Act: -0.1700
Data Index: 3489594 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.6921. Min Act: -0.1700
Data Index: 2844538 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.5671. Min Act: -0.1700
Data Index: 7857051 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.5984. Min Act: -0.1700
Data Index: 3724553 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.5359. Min Act: -0.1700
Data Index: 6434376 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.5359. Min Act: -0.1700
Data Index: 617343 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.5046. Min Act: -0.1700
Data Index: 6036442 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.4109. Min Act: -0.1700
Data Index: 8108629 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.3484. Min Act: -0.1700
Data Index: 6476520 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.2859. Min Act: -0.1700
Data Index: 3047765 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.3171. Min Act: -0.1700
Data Index: 144818 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.3171. Min Act: -0.1700
Data Index: 144814 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.2859. Min Act: -0.1700
Data Index: 3724548 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.3171. Min Act: -0.1700
Data Index: 6476516 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.2859. Min Act: -0.1700
Data Index: 5233564 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.2859. Min Act: -0.1700
Data Index: 8331632 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.2859. Min Act: -0.1700
Data Index: 3724551 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8796. Min Range: -5.8796
Max Act: 5.2859. Min Act: -0.1700
Data Index: 5600126 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19