Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3945 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0946. Min Range: -3.0946
Max Act: 3.0946. Min Act: -0.1700
Data Index: 886953 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0946. Min Range: -3.0946
Max Act: 3.0157. Min Act: -0.1700
Data Index: 8715888 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9208. Min Act: -0.1700
Data Index: 5517349 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.9049. Min Act: -0.1700
Data Index: 1889088 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.8891. Min Act: -0.1700
Data Index: 7847237 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.8573. Min Act: -0.1700
Data Index: 5340502 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.8414. Min Act: -0.1700
Data Index: 3147269 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.8414. Min Act: -0.1700
Data Index: 3565515 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.7778. Min Act: -0.1700
Data Index: 7637257 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.7937. Min Act: -0.1700
Data Index: 4241110 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.7778. Min Act: -0.1700
Data Index: 5614844 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.7618. Min Act: -0.1700
Data Index: 7973300 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.7459. Min Act: -0.1700
Data Index: 3648151 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.7459. Min Act: -0.1700
Data Index: 8098212 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.7459. Min Act: -0.1700
Data Index: 4806547 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.7299. Min Act: -0.1700
Data Index: 3348414 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.6979. Min Act: -0.1700
Data Index: 261571 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.7139. Min Act: -0.1700
Data Index: 1345536 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.7139. Min Act: -0.1700
Data Index: 6762030 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0946. Min Range: -3.0946
Max Act: 2.7299. Min Act: -0.1700
Data Index: 6820558 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19