Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4030 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.7970. Min Act: -0.1700
Data Index: 6427407 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.6095. Min Act: -0.1700
Data Index: 7092356 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.5157. Min Act: -0.1700
Data Index: 4190827 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.5157. Min Act: -0.1700
Data Index: 8639679 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.5157. Min Act: -0.1700
Data Index: 8283009 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.4845. Min Act: -0.1700
Data Index: 397315 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.4532. Min Act: -0.1700
Data Index: 1888980 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.4845. Min Act: -0.1700
Data Index: 4382434 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.4532. Min Act: -0.1700
Data Index: 3397937 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.3907. Min Act: -0.1700
Data Index: 2058292 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.3595. Min Act: -0.1700
Data Index: 4347098 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.3595. Min Act: -0.1700
Data Index: 6443113 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.3595. Min Act: -0.1700
Data Index: 1671746 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.3595. Min Act: -0.1700
Data Index: 5043790 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.3595. Min Act: -0.1700
Data Index: 2080597 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.3595. Min Act: -0.1700
Data Index: 296947 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.3595. Min Act: -0.1700
Data Index: 3197366 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.3595. Min Act: -0.1700
Data Index: 6089196 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.3282. Min Act: -0.1700
Data Index: 3031467 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7970. Min Range: -6.7970
Max Act: 6.3282. Min Act: -0.1700
Data Index: 5866387 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19