Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1969 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.3477. Min Act: -0.1700
Data Index: 3140702 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.3389. Min Act: -0.1700
Data Index: 8803327 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.3389. Min Act: -0.1700
Data Index: 7909329 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.3213. Min Act: -0.1700
Data Index: 2929515 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.3301. Min Act: -0.1700
Data Index: 7183030 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.3125. Min Act: -0.1700
Data Index: 373907 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.3036. Min Act: -0.1700
Data Index: 1153934 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.3125. Min Act: -0.1700
Data Index: 3701334 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.2948. Min Act: -0.1700
Data Index: 5726516 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.2948. Min Act: -0.1700
Data Index: 4355137 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.3036. Min Act: -0.1700
Data Index: 1296259 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.2948. Min Act: -0.1700
Data Index: 3377640 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.2948. Min Act: -0.1700
Data Index: 2843066 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.2860. Min Act: -0.1700
Data Index: 8392909 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.2948. Min Act: -0.1700
Data Index: 3626498 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.2948. Min Act: -0.1700
Data Index: 5791008 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.2772. Min Act: -0.1700
Data Index: 8324755 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.2507. Min Act: -0.1700
Data Index: 2923912 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.2772. Min Act: -0.1700
Data Index: 5208450 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3477. Min Range: -1.3477
Max Act: 1.2860. Min Act: -0.1700
Data Index: 8297455 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19