Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3873 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.6811. Min Act: -0.1700
Data Index: 7385754 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.7124. Min Act: -0.1700
Data Index: 6160880 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.6186. Min Act: -0.1700
Data Index: 2316766 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.6186. Min Act: -0.1700
Data Index: 2509675 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.6029. Min Act: -0.1700
Data Index: 8042444 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.5716. Min Act: -0.1700
Data Index: 788122 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.5716. Min Act: -0.1700
Data Index: 1582304 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.5716. Min Act: -0.1700
Data Index: 41749 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.5559. Min Act: -0.1700
Data Index: 3973586 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.5403. Min Act: -0.1700
Data Index: 877859 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.5403. Min Act: -0.1700
Data Index: 1666388 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.5246. Min Act: -0.1700
Data Index: 8670904 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.5090. Min Act: -0.1700
Data Index: 2509674 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.5090. Min Act: -0.1700
Data Index: 585026 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4933. Min Act: -0.1700
Data Index: 4789863 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4933. Min Act: -0.1700
Data Index: 4587977 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.5090. Min Act: -0.1700
Data Index: 6834686 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4463. Min Act: -0.1700
Data Index: 178354 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4776. Min Act: -0.1700
Data Index: 6081022 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4463. Min Act: -0.1700
Data Index: 780374 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19