Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 858 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.7834. Min Act: -0.1700
Data Index: 2461206 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.5647. Min Act: -0.1700
Data Index: 7963472 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.3772. Min Act: -0.1700
Data Index: 2353486 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.3147. Min Act: -0.1700
Data Index: 2319466 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.3147. Min Act: -0.1700
Data Index: 723325 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.2209. Min Act: -0.1700
Data Index: 3662786 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.2209. Min Act: -0.1700
Data Index: 42883 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.2209. Min Act: -0.1700
Data Index: 4411224 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.1897. Min Act: -0.1700
Data Index: 6119100 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.1897. Min Act: -0.1700
Data Index: 3840368 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.1897. Min Act: -0.1700
Data Index: 4858346 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.1584. Min Act: -0.1700
Data Index: 609539 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.0959. Min Act: -0.1700
Data Index: 1873981 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.0959. Min Act: -0.1700
Data Index: 7470361 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.0334. Min Act: -0.1700
Data Index: 309694 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.0334. Min Act: -0.1700
Data Index: 7650542 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.0334. Min Act: -0.1700
Data Index: 7214469 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7834. Min Range: -5.7834
Max Act: 5.0022. Min Act: -0.1700
Data Index: 4838093 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7834. Min Range: -5.7834
Max Act: 4.9709. Min Act: -0.1700
Data Index: 4113202 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7834. Min Range: -5.7834
Max Act: 4.9709. Min Act: -0.1700
Data Index: 1009995 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19