Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1429 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.4466. Min Act: -0.1700
Data Index: 6646452 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.4154. Min Act: -0.1700
Data Index: 8462686 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.4154. Min Act: -0.1700
Data Index: 944991 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.3841. Min Act: -0.1700
Data Index: 5966152 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.3529. Min Act: -0.1700
Data Index: 7377846 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.3216. Min Act: -0.1700
Data Index: 6134466 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.2904. Min Act: -0.1700
Data Index: 8045549 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.3216. Min Act: -0.1700
Data Index: 602750 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.2591. Min Act: -0.1700
Data Index: 2611529 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.2591. Min Act: -0.1700
Data Index: 8323633 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.2904. Min Act: -0.1700
Data Index: 5051036 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.2279. Min Act: -0.1700
Data Index: 6297480 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.2279. Min Act: -0.1700
Data Index: 7349046 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.2591. Min Act: -0.1700
Data Index: 7190722 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.1966. Min Act: -0.1700
Data Index: 1012797 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.1966. Min Act: -0.1700
Data Index: 6759060 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.1966. Min Act: -0.1700
Data Index: 3275875 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.1966. Min Act: -0.1700
Data Index: 4767116 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.1341. Min Act: -0.1700
Data Index: 4785021 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4466. Min Range: -5.4466
Max Act: 5.1966. Min Act: -0.1700
Data Index: 169910 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19