Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0315. Min Range: -2.0315
Max Act: 2.0315. Min Act: -0.1700
Data Index: 7798683 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9893. Min Act: -0.1698
Data Index: 353355 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9893. Min Act: -0.1700
Data Index: 5085628 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9639. Min Act: -0.1700
Data Index: 8074666 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9554. Min Act: -0.1700
Data Index: 7296731 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9469. Min Act: -0.1700
Data Index: 8165672 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9554. Min Act: -0.1700
Data Index: 3432087 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9554. Min Act: -0.1700
Data Index: 2245820 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9469. Min Act: -0.1700
Data Index: 5265536 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9299. Min Act: -0.1699
Data Index: 7499955 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9299. Min Act: -0.1700
Data Index: 909488 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9384. Min Act: -0.1700
Data Index: 5942169 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9214. Min Act: -0.1699
Data Index: 199271 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9214. Min Act: -0.1700
Data Index: 3800202 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9299. Min Act: -0.1699
Data Index: 2267264 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9214. Min Act: -0.1693
Data Index: 5275046 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9129. Min Act: -0.1700
Data Index: 7195829 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9044. Min Act: -0.1699
Data Index: 4350400 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9044. Min Act: -0.1700
Data Index: 5859914 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0315. Min Range: -2.0315
Max Act: 1.9129. Min Act: -0.1700
Data Index: 1555985 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19