Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 302 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.5178. Min Act: -0.1700
Data Index: 2476567 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.5490. Min Act: -0.1700
Data Index: 7220146 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.4240. Min Act: -0.1700
Data Index: 6122000 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.3615. Min Act: -0.1700
Data Index: 113044 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.3303. Min Act: -0.1700
Data Index: 3607061 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.3303. Min Act: -0.1700
Data Index: 3096564 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.2678. Min Act: -0.1700
Data Index: 7676478 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.2678. Min Act: -0.1700
Data Index: 201283 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.2053. Min Act: -0.1700
Data Index: 7422456 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.2678. Min Act: -0.1700
Data Index: 4338307 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.2365. Min Act: -0.1700
Data Index: 4839166 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.1740. Min Act: -0.1700
Data Index: 3599093 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.1115. Min Act: -0.1700
Data Index: 8622021 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.0490. Min Act: -0.1700
Data Index: 3024480 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.1740. Min Act: -0.1700
Data Index: 1485845 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.0803. Min Act: -0.1700
Data Index: 7674047 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.0803. Min Act: -0.1700
Data Index: 3954445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.0803. Min Act: -0.1700
Data Index: 1009316 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.0178. Min Act: -0.1700
Data Index: 5565099 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5490. Min Range: -7.5490
Max Act: 7.0178. Min Act: -0.1700
Data Index: 2373164 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19