Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4785 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.7485. Min Act: -0.1700
Data Index: 5833741 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.6546. Min Act: -0.1700
Data Index: 5374464 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.6859. Min Act: -0.1700
Data Index: 5986900 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.6546. Min Act: -0.1700
Data Index: 2736405 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.6859. Min Act: -0.1700
Data Index: 844744 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.6859. Min Act: -0.1700
Data Index: 3017539 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.6233. Min Act: -0.1700
Data Index: 8598636 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.6233. Min Act: -0.1700
Data Index: 4707087 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.6233. Min Act: -0.1700
Data Index: 3050809 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.6233. Min Act: -0.1700
Data Index: 8484418 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.6233. Min Act: -0.1700
Data Index: 2431576 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.6233. Min Act: -0.1700
Data Index: 3050823 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.6233. Min Act: -0.1700
Data Index: 7215242 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.5920. Min Act: -0.1700
Data Index: 631190 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.5920. Min Act: -0.1700
Data Index: 4707086 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.5920. Min Act: -0.1700
Data Index: 3639654 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.5607. Min Act: -0.1700
Data Index: 7215243 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.5607. Min Act: -0.1700
Data Index: 6759541 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.5920. Min Act: -0.1700
Data Index: 3363000 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7485. Min Range: -3.7485
Max Act: 3.5607. Min Act: -0.1700
Data Index: 895062 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19