Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.5881. Min Act: -0.1700
Data Index: 5135699 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.6193. Min Act: -0.1700
Data Index: 4687878 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.5881. Min Act: -0.1700
Data Index: 1389135 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.4006. Min Act: -0.1700
Data Index: 5920025 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.4006. Min Act: -0.1700
Data Index: 4442204 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.3693. Min Act: -0.1700
Data Index: 2413789 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.3381. Min Act: -0.1700
Data Index: 8800544 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.3381. Min Act: -0.1700
Data Index: 8121015 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.2756. Min Act: -0.1700
Data Index: 6767419 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.3068. Min Act: -0.1700
Data Index: 1033551 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.3068. Min Act: -0.1700
Data Index: 4399933 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.3068. Min Act: -0.1700
Data Index: 8053678 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.3068. Min Act: -0.1700
Data Index: 5536339 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.3068. Min Act: -0.1700
Data Index: 2213233 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.2756. Min Act: -0.1700
Data Index: 7072643 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.2443. Min Act: -0.1700
Data Index: 992511 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.2443. Min Act: -0.1700
Data Index: 553230 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.2443. Min Act: -0.1700
Data Index: 7544128 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.2756. Min Act: -0.1700
Data Index: 3991733 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6193. Min Range: -6.6193
Max Act: 6.2756. Min Act: -0.1700
Data Index: 8098563 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19