Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1477 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.4415. Min Act: -0.1700
Data Index: 5833488 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.4103. Min Act: -0.1700
Data Index: 980403 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3790. Min Act: -0.1700
Data Index: 8555202 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.4103. Min Act: -0.1700
Data Index: 3560903 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.4103. Min Act: -0.1700
Data Index: 4618822 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3790. Min Act: -0.1700
Data Index: 3979278 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3478. Min Act: -0.1700
Data Index: 5066354 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3478. Min Act: -0.1700
Data Index: 3478112 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3790. Min Act: -0.1700
Data Index: 51316 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3790. Min Act: -0.1700
Data Index: 7201526 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3478. Min Act: -0.1700
Data Index: 1302641 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3790. Min Act: -0.1700
Data Index: 3335457 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3478. Min Act: -0.1700
Data Index: 5668818 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3790. Min Act: -0.1700
Data Index: 2062226 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3790. Min Act: -0.1700
Data Index: 8573858 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3478. Min Act: -0.1700
Data Index: 5125946 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.2853. Min Act: -0.1700
Data Index: 7201521 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3165. Min Act: -0.1700
Data Index: 1340922 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3165. Min Act: -0.1700
Data Index: 8763203 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4415. Min Range: -4.4415
Max Act: 4.3165. Min Act: -0.1700
Data Index: 189999 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19