Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1609 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.6057. Min Act: -0.1700
Data Index: 5737574 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.5432. Min Act: -0.1700
Data Index: 1300463 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.4807. Min Act: -0.1700
Data Index: 4340551 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.4494. Min Act: -0.1700
Data Index: 3287061 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.3557. Min Act: -0.1700
Data Index: 6875857 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.3244. Min Act: -0.1700
Data Index: 4880022 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.3244. Min Act: -0.1700
Data Index: 4428555 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.3244. Min Act: -0.1700
Data Index: 8433851 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.3244. Min Act: -0.1700
Data Index: 7468367 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.2932. Min Act: -0.1700
Data Index: 3226402 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.2619. Min Act: -0.1700
Data Index: 8468440 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.2619. Min Act: -0.1700
Data Index: 862139 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.2307. Min Act: -0.1700
Data Index: 4267973 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.2307. Min Act: -0.1700
Data Index: 5912637 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.1994. Min Act: -0.1700
Data Index: 2989736 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.1682. Min Act: -0.1700
Data Index: 1047487 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.1682. Min Act: -0.1700
Data Index: 3287077 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.1994. Min Act: -0.1700
Data Index: 7640023 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.1994. Min Act: -0.1700
Data Index: 1471000 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6057. Min Range: -6.6057
Max Act: 6.1369. Min Act: -0.1700
Data Index: 4239617 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19