Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2733 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.7657. Min Act: -0.1700
Data Index: 5894787 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.6720. Min Act: -0.1700
Data Index: 6234226 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.6407. Min Act: -0.1700
Data Index: 7532601 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.5470. Min Act: -0.1700
Data Index: 4037547 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.5470. Min Act: -0.1700
Data Index: 3226374 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.4845. Min Act: -0.1700
Data Index: 4119357 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.4532. Min Act: -0.1700
Data Index: 6381963 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.4220. Min Act: -0.1700
Data Index: 4566536 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.4532. Min Act: -0.1700
Data Index: 4851148 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.4532. Min Act: -0.1700
Data Index: 3441951 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.3907. Min Act: -0.1700
Data Index: 4106343 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.3595. Min Act: -0.1700
Data Index: 4218194 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.3595. Min Act: -0.1700
Data Index: 7374858 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.3282. Min Act: -0.1700
Data Index: 8737374 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.3282. Min Act: -0.1700
Data Index: 219473 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.3282. Min Act: -0.1700
Data Index: 6287707 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.2970. Min Act: -0.1700
Data Index: 8487926 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.2970. Min Act: -0.1700
Data Index: 4788521 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.2657. Min Act: -0.1700
Data Index: 4762310 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7657. Min Range: -5.7657
Max Act: 5.2970. Min Act: -0.1700
Data Index: 489019 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19