Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.4397. Min Act: -0.1700
Data Index: 929552 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.2834. Min Act: -0.1700
Data Index: 1094386 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.2522. Min Act: -0.1700
Data Index: 5026150 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.2522. Min Act: -0.1700
Data Index: 3011643 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.1897. Min Act: -0.1700
Data Index: 1782912 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.1272. Min Act: -0.1700
Data Index: 4206782 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.1584. Min Act: -0.1700
Data Index: 6994337 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.1272. Min Act: -0.1700
Data Index: 6730412 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.1272. Min Act: -0.1700
Data Index: 4549677 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.1272. Min Act: -0.1700
Data Index: 7575332 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.0959. Min Act: -0.1700
Data Index: 7664078 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.0959. Min Act: -0.1700
Data Index: 2813683 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.0959. Min Act: -0.1700
Data Index: 6044736 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.0959. Min Act: -0.1700
Data Index: 6710512 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.0959. Min Act: -0.1700
Data Index: 7653526 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.0959. Min Act: -0.1700
Data Index: 4750700 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.0647. Min Act: -0.1700
Data Index: 544313 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.0647. Min Act: -0.1700
Data Index: 1653708 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.0647. Min Act: -0.1700
Data Index: 6753439 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4397. Min Range: -5.4397
Max Act: 5.0647. Min Act: -0.1700
Data Index: 4678809 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19