Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3703 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4449. Min Range: -5.4449
Max Act: 5.4449. Min Act: -0.1700
Data Index: 1460455 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4449. Min Range: -5.4449
Max Act: 5.2574. Min Act: -0.1700
Data Index: 1075321 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4449. Min Range: -5.4449
Max Act: 5.1324. Min Act: -0.1700
Data Index: 1460457 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4449. Min Range: -5.4449
Max Act: 5.0074. Min Act: -0.1700
Data Index: 1708247 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.9761. Min Act: -0.1700
Data Index: 3151233 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.9761. Min Act: -0.1700
Data Index: 7494226 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.9136. Min Act: -0.1700
Data Index: 3750327 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.9449. Min Act: -0.1700
Data Index: 4820863 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.9449. Min Act: -0.1700
Data Index: 3229595 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.8511. Min Act: -0.1700
Data Index: 4621238 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.8824. Min Act: -0.1700
Data Index: 697852 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.8824. Min Act: -0.1700
Data Index: 8480013 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.8511. Min Act: -0.1700
Data Index: 3229594 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.8199. Min Act: -0.1700
Data Index: 8051512 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.8199. Min Act: -0.1700
Data Index: 6627844 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.8199. Min Act: -0.1700
Data Index: 1536439 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.8199. Min Act: -0.1700
Data Index: 2891824 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.8199. Min Act: -0.1700
Data Index: 3500190 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.7886. Min Act: -0.1700
Data Index: 823521 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4449. Min Range: -5.4449
Max Act: 4.8199. Min Act: -0.1700
Data Index: 6489474 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19