Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.4341. Min Act: -0.1700
Data Index: 2093378 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.4028. Min Act: -0.1700
Data Index: 7802902 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.3716. Min Act: -0.1700
Data Index: 4482681 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.3403. Min Act: -0.1700
Data Index: 2041571 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.3091. Min Act: -0.1700
Data Index: 7580482 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.2466. Min Act: -0.1700
Data Index: 3689996 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.2466. Min Act: -0.1700
Data Index: 2426238 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.2466. Min Act: -0.1700
Data Index: 5664541 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.2778. Min Act: -0.1700
Data Index: 8382408 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.2466. Min Act: -0.1700
Data Index: 3671037 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.2466. Min Act: -0.1700
Data Index: 6448029 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.2153. Min Act: -0.1700
Data Index: 6908240 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.2153. Min Act: -0.1700
Data Index: 6361133 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.2153. Min Act: -0.1700
Data Index: 458293 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.1841. Min Act: -0.1700
Data Index: 8649024 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.1841. Min Act: -0.1700
Data Index: 3327515 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.1528. Min Act: -0.1700
Data Index: 3039344 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.1528. Min Act: -0.1700
Data Index: 5926830 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.1528. Min Act: -0.1700
Data Index: 6408838 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4341. Min Range: -5.4341
Max Act: 5.1528. Min Act: -0.1700
Data Index: 7123101 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19