Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3861. Min Act: -0.1700
Data Index: 5948503 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3861. Min Act: -0.1700
Data Index: 7135686 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3861. Min Act: -0.1700
Data Index: 4063396 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3533. Min Act: -0.1700
Data Index: 1007706 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3370. Min Act: -0.1700
Data Index: 3114127 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3370. Min Act: -0.1700
Data Index: 2812815 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3370. Min Act: -0.1700
Data Index: 7406016 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3370. Min Act: -0.1700
Data Index: 2249027 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3370. Min Act: -0.1700
Data Index: 1826422 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3205. Min Act: -0.1700
Data Index: 2019343 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3205. Min Act: -0.1700
Data Index: 17597 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3041. Min Act: -0.1700
Data Index: 6557503 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3041. Min Act: -0.1700
Data Index: 8273324 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.3041. Min Act: -0.1700
Data Index: 8591430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.2877. Min Act: -0.1700
Data Index: 4677734 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.2877. Min Act: -0.1700
Data Index: 859244 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.2877. Min Act: -0.1700
Data Index: 6487180 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.2877. Min Act: -0.1700
Data Index: 7525661 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.2877. Min Act: -0.1700
Data Index: 2779140 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3861. Min Range: -2.3861
Max Act: 2.2877. Min Act: -0.1700
Data Index: 6035983 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19