Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 348 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8285. Min Range: -6.8285
Max Act: 6.8285. Min Act: -0.1700
Data Index: 6159645 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8285. Min Range: -6.8285
Max Act: 6.2347. Min Act: -0.1700
Data Index: 7788236 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8285. Min Range: -6.8285
Max Act: 6.2035. Min Act: -0.1700
Data Index: 1288695 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8285. Min Range: -6.8285
Max Act: 6.2035. Min Act: -0.1700
Data Index: 4865505 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8285. Min Range: -6.8285
Max Act: 6.2035. Min Act: -0.1700
Data Index: 3592049 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8285. Min Range: -6.8285
Max Act: 6.0472. Min Act: -0.1700
Data Index: 7211532 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8285. Min Range: -6.8285
Max Act: 6.0472. Min Act: -0.1700
Data Index: 5309336 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8285. Min Range: -6.8285
Max Act: 6.0160. Min Act: -0.1700
Data Index: 708086 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8285. Min Range: -6.8285
Max Act: 5.9847. Min Act: -0.1700
Data Index: 393308 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8285. Min Range: -6.8285
Max Act: 5.9535. Min Act: -0.1700
Data Index: 1577199 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8285. Min Range: -6.8285
Max Act: 5.9535. Min Act: -0.1700
Data Index: 4156397 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8285. Min Range: -6.8285
Max Act: 5.9535. Min Act: -0.1700
Data Index: 2973068 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8285. Min Range: -6.8285
Max Act: 5.9535. Min Act: -0.1700
Data Index: 3235103 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8285. Min Range: -6.8285
Max Act: 5.9535. Min Act: -0.1700
Data Index: 8646008 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8285. Min Range: -6.8285
Max Act: 5.8910. Min Act: -0.1700
Data Index: 5120641 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8285. Min Range: -6.8285
Max Act: 5.8910. Min Act: -0.1700
Data Index: 5485045 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8285. Min Range: -6.8285
Max Act: 5.8910. Min Act: -0.1700
Data Index: 8602469 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8285. Min Range: -6.8285
Max Act: 5.9222. Min Act: -0.1700
Data Index: 8016927 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8285. Min Range: -6.8285
Max Act: 5.8910. Min Act: -0.1700
Data Index: 6622741 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8285. Min Range: -6.8285
Max Act: 5.7972. Min Act: -0.1700
Data Index: 3899858 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19