Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.9404. Min Act: -0.1700
Data Index: 7789614 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.9091. Min Act: -0.1700
Data Index: 3753669 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.8779. Min Act: -0.1700
Data Index: 4606768 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.8154. Min Act: -0.1700
Data Index: 5755481 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.8154. Min Act: -0.1700
Data Index: 2803640 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.7841. Min Act: -0.1700
Data Index: 334966 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.7841. Min Act: -0.1700
Data Index: 1664286 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.7529. Min Act: -0.1700
Data Index: 5755482 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.7529. Min Act: -0.1700
Data Index: 1144282 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.6904. Min Act: -0.1700
Data Index: 486919 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.6591. Min Act: -0.1700
Data Index: 4537282 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.6904. Min Act: -0.1700
Data Index: 7028303 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.6904. Min Act: -0.1700
Data Index: 4537280 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.6591. Min Act: -0.1700
Data Index: 1108784 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.6279. Min Act: -0.1700
Data Index: 6090187 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.5966. Min Act: -0.1700
Data Index: 5347963 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.6279. Min Act: -0.1700
Data Index: 4313136 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.6279. Min Act: -0.1700
Data Index: 7515010 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.6279. Min Act: -0.1700
Data Index: 3182194 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9404. Min Range: -4.9404
Max Act: 4.6279. Min Act: -0.1700
Data Index: 4537279 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19