Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 901 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0241. Min Range: -5.0241
Max Act: 5.0241. Min Act: -0.1700
Data Index: 1407876 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.9928. Min Act: -0.1700
Data Index: 6314477 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.7116. Min Act: -0.1700
Data Index: 3694805 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.7116. Min Act: -0.1700
Data Index: 6111731 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.7116. Min Act: -0.1700
Data Index: 8281013 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.6803. Min Act: -0.1700
Data Index: 6093974 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.6178. Min Act: -0.1700
Data Index: 8703105 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.5866. Min Act: -0.1700
Data Index: 5936352 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.5866. Min Act: -0.1700
Data Index: 4963078 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.5553. Min Act: -0.1700
Data Index: 6115864 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.5553. Min Act: -0.1700
Data Index: 4934205 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.5553. Min Act: -0.1700
Data Index: 4319050 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.5553. Min Act: -0.1700
Data Index: 7359591 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.5241. Min Act: -0.1700
Data Index: 2855015 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.4928. Min Act: -0.1700
Data Index: 7948460 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.4928. Min Act: -0.1700
Data Index: 8349531 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.5241. Min Act: -0.1700
Data Index: 292320 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.4928. Min Act: -0.1700
Data Index: 8510477 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.4616. Min Act: -0.1700
Data Index: 2153033 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0241. Min Range: -5.0241
Max Act: 4.4303. Min Act: -0.1700
Data Index: 2836632 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19