Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 387 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5320. Min Range: -7.5320
Max Act: 7.5320. Min Act: -0.1700
Data Index: 3818321 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5320. Min Range: -7.5320
Max Act: 7.4383. Min Act: -0.1700
Data Index: 5678302 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5320. Min Range: -7.5320
Max Act: 7.2820. Min Act: -0.1700
Data Index: 5678301 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5320. Min Range: -7.5320
Max Act: 7.3133. Min Act: -0.1700
Data Index: 6191392 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5320. Min Range: -7.5320
Max Act: 7.2508. Min Act: -0.1700
Data Index: 358922 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5320. Min Range: -7.5320
Max Act: 7.1258. Min Act: -0.1700
Data Index: 2327950 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5320. Min Range: -7.5320
Max Act: 7.1258. Min Act: -0.1700
Data Index: 3818320 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5320. Min Range: -7.5320
Max Act: 7.0945. Min Act: -0.1700
Data Index: 1252963 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5320. Min Range: -7.5320
Max Act: 6.9383. Min Act: -0.1700
Data Index: 358921 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5320. Min Range: -7.5320
Max Act: 6.9070. Min Act: -0.1700
Data Index: 8404778 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5320. Min Range: -7.5320
Max Act: 6.9383. Min Act: -0.1700
Data Index: 6191391 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5320. Min Range: -7.5320
Max Act: 6.8758. Min Act: -0.1700
Data Index: 2498329 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5320. Min Range: -7.5320
Max Act: 6.8758. Min Act: -0.1700
Data Index: 1252965 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5320. Min Range: -7.5320
Max Act: 6.8445. Min Act: -0.1700
Data Index: 7811848 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5320. Min Range: -7.5320
Max Act: 6.7508. Min Act: -0.1700
Data Index: 6339693 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5320. Min Range: -7.5320
Max Act: 6.7195. Min Act: -0.1700
Data Index: 8255601 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5320. Min Range: -7.5320
Max Act: 6.6883. Min Act: -0.1700
Data Index: 4947317 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5320. Min Range: -7.5320
Max Act: 6.6570. Min Act: -0.1700
Data Index: 3261426 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5320. Min Range: -7.5320
Max Act: 6.6883. Min Act: -0.1700
Data Index: 4806185 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5320. Min Range: -7.5320
Max Act: 6.6570. Min Act: -0.1700
Data Index: 257411 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19