Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4952. Min Range: -10.4952
Max Act: 10.4952. Min Act: -0.1700
Data Index: 7878570 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4952. Min Range: -10.4952
Max Act: 10.3702. Min Act: -0.1700
Data Index: 1295738 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4952. Min Range: -10.4952
Max Act: 10.1827. Min Act: -0.1700
Data Index: 3883013 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.9952. Min Act: -0.1700
Data Index: 2981335 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4952. Min Range: -10.4952
Max Act: 10.0577. Min Act: -0.1700
Data Index: 5825784 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4952. Min Range: -10.4952
Max Act: 10.0577. Min Act: -0.1700
Data Index: 3652837 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.8702. Min Act: -0.1700
Data Index: 5252027 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.8077. Min Act: -0.1700
Data Index: 7885153 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.8077. Min Act: -0.1700
Data Index: 7449268 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.7452. Min Act: -0.1700
Data Index: 3602614 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.7452. Min Act: -0.1700
Data Index: 1367619 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.6827. Min Act: -0.1700
Data Index: 8733054 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.6827. Min Act: -0.1700
Data Index: 7713228 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.6202. Min Act: -0.1700
Data Index: 436253 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.6202. Min Act: -0.1700
Data Index: 7606564 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.6827. Min Act: -0.1700
Data Index: 3167998 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.5577. Min Act: -0.1700
Data Index: 5751501 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.5577. Min Act: -0.1700
Data Index: 7792254 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.5577. Min Act: -0.1700
Data Index: 2857593 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4952. Min Range: -10.4952
Max Act: 9.5577. Min Act: -0.1700
Data Index: 5363295 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19