Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2485 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2848. Min Range: -7.2848
Max Act: 7.2848. Min Act: -0.1700
Data Index: 8477958 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.9098. Min Act: -0.1700
Data Index: 1863541 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.9098. Min Act: -0.1700
Data Index: 4558084 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.8473. Min Act: -0.1700
Data Index: 4416003 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.8160. Min Act: -0.1700
Data Index: 2658606 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.8160. Min Act: -0.1700
Data Index: 5825469 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.7848. Min Act: -0.1700
Data Index: 3268927 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.7223. Min Act: -0.1700
Data Index: 6299419 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.7535. Min Act: -0.1700
Data Index: 3777328 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.6910. Min Act: -0.1700
Data Index: 2919224 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.6910. Min Act: -0.1700
Data Index: 4511277 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.6910. Min Act: -0.1700
Data Index: 1830460 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.6285. Min Act: -0.1700
Data Index: 6122880 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.6598. Min Act: -0.1700
Data Index: 2276081 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.6285. Min Act: -0.1700
Data Index: 3647389 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.6285. Min Act: -0.1700
Data Index: 2120649 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.5973. Min Act: -0.1700
Data Index: 1973449 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.5973. Min Act: -0.1700
Data Index: 3545421 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.5973. Min Act: -0.1700
Data Index: 6334320 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2848. Min Range: -7.2848
Max Act: 6.5660. Min Act: -0.1700
Data Index: 7940425 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19