Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.7635. Min Act: -0.1700
Data Index: 4930828 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.5448. Min Act: -0.1700
Data Index: 6667553 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.4823. Min Act: -0.1700
Data Index: 2722365 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.5135. Min Act: -0.1700
Data Index: 2408609 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.4823. Min Act: -0.1700
Data Index: 1217611 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.5135. Min Act: -0.1700
Data Index: 5048537 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.4510. Min Act: -0.1700
Data Index: 756189 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.4510. Min Act: -0.1700
Data Index: 4661038 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.4510. Min Act: -0.1700
Data Index: 2548664 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.4198. Min Act: -0.1700
Data Index: 3029888 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.4198. Min Act: -0.1700
Data Index: 212222 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.3885. Min Act: -0.1700
Data Index: 547225 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.3885. Min Act: -0.1700
Data Index: 5036530 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.3885. Min Act: -0.1700
Data Index: 6900195 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.3885. Min Act: -0.1700
Data Index: 5270437 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.3885. Min Act: -0.1700
Data Index: 2350162 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.3260. Min Act: -0.1700
Data Index: 1821464 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.3260. Min Act: -0.1700
Data Index: 6019276 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.2948. Min Act: -0.1700
Data Index: 4511909 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7635. Min Range: -6.7635
Max Act: 6.2948. Min Act: -0.1700
Data Index: 5340494 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19