Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4814 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9148. Min Range: -5.9148
Max Act: 5.9148. Min Act: -0.1700
Data Index: 8245160 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9148. Min Range: -5.9148
Max Act: 5.6023. Min Act: -0.1700
Data Index: 2743906 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9148. Min Range: -5.9148
Max Act: 5.5711. Min Act: -0.1700
Data Index: 5649768 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9148. Min Range: -5.9148
Max Act: 5.3836. Min Act: -0.1700
Data Index: 6064699 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9148. Min Range: -5.9148
Max Act: 5.2273. Min Act: -0.1700
Data Index: 7238046 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9148. Min Range: -5.9148
Max Act: 5.1336. Min Act: -0.1700
Data Index: 2531326 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9148. Min Range: -5.9148
Max Act: 5.1023. Min Act: -0.1700
Data Index: 8454465 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9148. Min Range: -5.9148
Max Act: 5.0086. Min Act: -0.1700
Data Index: 2802855 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9148. Min Range: -5.9148
Max Act: 4.9773. Min Act: -0.1700
Data Index: 429869 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9148. Min Range: -5.9148
Max Act: 4.9773. Min Act: -0.1700
Data Index: 918332 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9148. Min Range: -5.9148
Max Act: 4.9773. Min Act: -0.1700
Data Index: 4215577 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9148. Min Range: -5.9148
Max Act: 4.9461. Min Act: -0.1700
Data Index: 2732409 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9148. Min Range: -5.9148
Max Act: 4.9461. Min Act: -0.1700
Data Index: 2365702 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9148. Min Range: -5.9148
Max Act: 4.9461. Min Act: -0.1700
Data Index: 7723242 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9148. Min Range: -5.9148
Max Act: 4.9461. Min Act: -0.1700
Data Index: 4234382 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9148. Min Range: -5.9148
Max Act: 4.8836. Min Act: -0.1700
Data Index: 8150625 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9148. Min Range: -5.9148
Max Act: 4.8836. Min Act: -0.1700
Data Index: 6064698 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9148. Min Range: -5.9148
Max Act: 4.8836. Min Act: -0.1700
Data Index: 6706832 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9148. Min Range: -5.9148
Max Act: 4.8523. Min Act: -0.1700
Data Index: 79904 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9148. Min Range: -5.9148
Max Act: 4.8211. Min Act: -0.1700
Data Index: 1207864 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19