Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4836 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.8368. Min Act: -0.1700
Data Index: 235272 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.8050. Min Act: -0.1700
Data Index: 2308125 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.7891. Min Act: -0.1700
Data Index: 1378899 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.7731. Min Act: -0.1700
Data Index: 2793529 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.7891. Min Act: -0.1700
Data Index: 1262063 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.7572. Min Act: -0.1700
Data Index: 4586342 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.7572. Min Act: -0.1700
Data Index: 3432865 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.7412. Min Act: -0.1700
Data Index: 3549 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.7412. Min Act: -0.1700
Data Index: 3859423 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.7252. Min Act: -0.1700
Data Index: 7995783 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.6932. Min Act: -0.1700
Data Index: 2076948 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.7092. Min Act: -0.1700
Data Index: 49655 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.6932. Min Act: -0.1700
Data Index: 6065151 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.6772. Min Act: -0.1700
Data Index: 3076073 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.6612. Min Act: -0.1700
Data Index: 6654155 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.6612. Min Act: -0.1700
Data Index: 8613852 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.6291. Min Act: -0.1700
Data Index: 5630322 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.6291. Min Act: -0.1700
Data Index: 1616684 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.6452. Min Act: -0.1700
Data Index: 4473089 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8368. Min Range: -2.8368
Max Act: 2.6452. Min Act: -0.1700
Data Index: 1985791 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19