Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2520 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.6374. Min Act: -0.1700
Data Index: 774448 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.6687. Min Act: -0.1700
Data Index: 4630318 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.6062. Min Act: -0.1700
Data Index: 3778504 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.5749. Min Act: -0.1700
Data Index: 1872816 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.5437. Min Act: -0.1700
Data Index: 6316466 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.5749. Min Act: -0.1700
Data Index: 2384327 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.5749. Min Act: -0.1700
Data Index: 106356 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.5437. Min Act: -0.1700
Data Index: 8629336 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.5124. Min Act: -0.1700
Data Index: 7621271 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.5749. Min Act: -0.1700
Data Index: 2147615 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.5437. Min Act: -0.1700
Data Index: 4550072 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.5124. Min Act: -0.1700
Data Index: 2618073 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.5124. Min Act: -0.1700
Data Index: 8366340 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.5124. Min Act: -0.1700
Data Index: 593551 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.5124. Min Act: -0.1700
Data Index: 6020786 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.4812. Min Act: -0.1700
Data Index: 4837216 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.4812. Min Act: -0.1700
Data Index: 2868229 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.4812. Min Act: -0.1700
Data Index: 87859 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.4499. Min Act: -0.1700
Data Index: 7118654 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6687. Min Range: -4.6687
Max Act: 4.4499. Min Act: -0.1700
Data Index: 7822293 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19