Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 747 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.5085. Min Act: -0.1700
Data Index: 2897364 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.5085. Min Act: -0.1700
Data Index: 5157573 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.4773. Min Act: -0.1700
Data Index: 8476844 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.4773. Min Act: -0.1700
Data Index: 6369151 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.4773. Min Act: -0.1700
Data Index: 1902778 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.4460. Min Act: -0.1700
Data Index: 2526260 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.4460. Min Act: -0.1700
Data Index: 2151708 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.4460. Min Act: -0.1700
Data Index: 3527017 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.4460. Min Act: -0.1700
Data Index: 5383174 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.4148. Min Act: -0.1700
Data Index: 5991759 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.4148. Min Act: -0.1700
Data Index: 8039415 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.3835. Min Act: -0.1700
Data Index: 144479 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.3835. Min Act: -0.1700
Data Index: 694389 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.3835. Min Act: -0.1700
Data Index: 4279261 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.3835. Min Act: -0.1700
Data Index: 3558044 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.3523. Min Act: -0.1700
Data Index: 6695059 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.3523. Min Act: -0.1700
Data Index: 2885858 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.3523. Min Act: -0.1700
Data Index: 8377796 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.3210. Min Act: -0.1700
Data Index: 6497765 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5085. Min Range: -6.5085
Max Act: 6.3835. Min Act: -0.1700
Data Index: 116230 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19