Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0107. Min Range: -4.0107
Max Act: 4.0107. Min Act: -0.1700
Data Index: 4707510 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.8856. Min Act: -0.1700
Data Index: 8733661 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.8856. Min Act: -0.1700
Data Index: 1097754 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.8856. Min Act: -0.1700
Data Index: 2197702 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.8544. Min Act: -0.1700
Data Index: 5995924 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.8544. Min Act: -0.1700
Data Index: 1314115 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.8544. Min Act: -0.1700
Data Index: 1242564 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.8231. Min Act: -0.1700
Data Index: 3984515 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.8544. Min Act: -0.1700
Data Index: 6620643 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.8544. Min Act: -0.1700
Data Index: 3449266 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.7918. Min Act: -0.1700
Data Index: 7552978 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.8231. Min Act: -0.1700
Data Index: 1705766 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.8231. Min Act: -0.1700
Data Index: 2534608 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.8231. Min Act: -0.1700
Data Index: 1242563 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.7918. Min Act: -0.1699
Data Index: 4165602 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.7918. Min Act: -0.1700
Data Index: 4256202 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.7918. Min Act: -0.1700
Data Index: 4458602 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.7918. Min Act: -0.1700
Data Index: 239926 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.7918. Min Act: -0.1700
Data Index: 314342 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0107. Min Range: -4.0107
Max Act: 3.7918. Min Act: -0.1700
Data Index: 2819372 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19