Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7124. Min Range: -7.7124
Max Act: 7.7124. Min Act: -0.1700
Data Index: 4430107 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7124. Min Range: -7.7124
Max Act: 7.3062. Min Act: -0.1700
Data Index: 8358983 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7124. Min Range: -7.7124
Max Act: 7.1812. Min Act: -0.1700
Data Index: 1326614 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7124. Min Range: -7.7124
Max Act: 7.1499. Min Act: -0.1700
Data Index: 1292261 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7124. Min Range: -7.7124
Max Act: 7.1187. Min Act: -0.1700
Data Index: 3741010 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7124. Min Range: -7.7124
Max Act: 7.1187. Min Act: -0.1700
Data Index: 2271798 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7124. Min Range: -7.7124
Max Act: 7.0874. Min Act: -0.1700
Data Index: 3583182 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7124. Min Range: -7.7124
Max Act: 7.0562. Min Act: -0.1700
Data Index: 5349368 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7124. Min Range: -7.7124
Max Act: 7.0249. Min Act: -0.1700
Data Index: 5701607 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7124. Min Range: -7.7124
Max Act: 7.0249. Min Act: -0.1700
Data Index: 6587556 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7124. Min Range: -7.7124
Max Act: 7.0249. Min Act: -0.1700
Data Index: 8148345 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7124. Min Range: -7.7124
Max Act: 6.9937. Min Act: -0.1700
Data Index: 191784 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7124. Min Range: -7.7124
Max Act: 6.9937. Min Act: -0.1700
Data Index: 852066 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7124. Min Range: -7.7124
Max Act: 6.9937. Min Act: -0.1700
Data Index: 3485845 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7124. Min Range: -7.7124
Max Act: 6.9624. Min Act: -0.1700
Data Index: 5776064 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7124. Min Range: -7.7124
Max Act: 6.9312. Min Act: -0.1700
Data Index: 4515197 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7124. Min Range: -7.7124
Max Act: 6.9937. Min Act: -0.1700
Data Index: 2321848 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7124. Min Range: -7.7124
Max Act: 6.8999. Min Act: -0.1700
Data Index: 483123 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7124. Min Range: -7.7124
Max Act: 6.8999. Min Act: -0.1700
Data Index: 857009 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7124. Min Range: -7.7124
Max Act: 6.9312. Min Act: -0.1700
Data Index: 4913335 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19