Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1177. Min Range: -4.1177
Max Act: 4.1177. Min Act: -0.1700
Data Index: 1236444 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.7738. Min Act: -0.1700
Data Index: 7687797 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.7425. Min Act: -0.1700
Data Index: 3932880 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.6956. Min Act: -0.1700
Data Index: 6908023 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.6486. Min Act: -0.1700
Data Index: 6253446 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.6643. Min Act: -0.1700
Data Index: 4606232 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.6330. Min Act: -0.1700
Data Index: 8030983 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.6486. Min Act: -0.1700
Data Index: 3799582 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.6330. Min Act: -0.1700
Data Index: 2352234 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.6330. Min Act: -0.1700
Data Index: 5383557 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.6173. Min Act: -0.1700
Data Index: 157872 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.6017. Min Act: -0.1700
Data Index: 7012883 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.5704. Min Act: -0.1700
Data Index: 497970 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.5860. Min Act: -0.1700
Data Index: 2224136 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.5860. Min Act: -0.1700
Data Index: 6515132 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.5704. Min Act: -0.1700
Data Index: 6481530 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.5704. Min Act: -0.1700
Data Index: 3559074 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.5547. Min Act: -0.1700
Data Index: 2050298 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.5547. Min Act: -0.1700
Data Index: 862557 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1177. Min Range: -4.1177
Max Act: 3.5547. Min Act: -0.1700
Data Index: 8160246 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19