Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.6281. Min Act: -0.1700
Data Index: 5349014 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.6125. Min Act: -0.1700
Data Index: 92622 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.5655. Min Act: -0.1700
Data Index: 4814771 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.4402. Min Act: -0.1700
Data Index: 2448605 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.4402. Min Act: -0.1700
Data Index: 3964003 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.4245. Min Act: -0.1700
Data Index: 8379309 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.4245. Min Act: -0.1700
Data Index: 2163726 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.4089. Min Act: -0.1700
Data Index: 1338166 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.4089. Min Act: -0.1700
Data Index: 3526141 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.3775. Min Act: -0.1700
Data Index: 3658387 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.3775. Min Act: -0.1700
Data Index: 8582874 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.3461. Min Act: -0.1700
Data Index: 686731 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.3305. Min Act: -0.1700
Data Index: 8582872 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.3305. Min Act: -0.1700
Data Index: 3642256 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.3305. Min Act: -0.1700
Data Index: 3190161 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.3305. Min Act: -0.1700
Data Index: 8582869 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.3148. Min Act: -0.1700
Data Index: 7381542 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.2834. Min Act: -0.1700
Data Index: 3100674 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.2834. Min Act: -0.1700
Data Index: 1079565 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6281. Min Range: -3.6281
Max Act: 3.2991. Min Act: -0.1700
Data Index: 5743609 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19