Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 594 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.3715. Min Act: -0.1700
Data Index: 2129588 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.3552. Min Act: -0.1700
Data Index: 7932200 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.3224. Min Act: -0.1700
Data Index: 5105759 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2895. Min Act: -0.1700
Data Index: 8055009 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2730. Min Act: -0.1700
Data Index: 8174452 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2895. Min Act: -0.1700
Data Index: 3232334 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2565. Min Act: -0.1700
Data Index: 1317179 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2565. Min Act: -0.1700
Data Index: 1915656 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2565. Min Act: -0.1700
Data Index: 679018 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2565. Min Act: -0.1700
Data Index: 8677076 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2234. Min Act: -0.1700
Data Index: 7731063 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2565. Min Act: -0.1700
Data Index: 1270904 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2400. Min Act: -0.1700
Data Index: 3300348 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2234. Min Act: -0.1700
Data Index: 563819 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2400. Min Act: -0.1700
Data Index: 6720650 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2234. Min Act: -0.1700
Data Index: 7885154 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2069. Min Act: -0.1700
Data Index: 6928710 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2234. Min Act: -0.1700
Data Index: 6213365 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2234. Min Act: -0.1700
Data Index: 1828709 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3715. Min Range: -2.3715
Max Act: 2.2234. Min Act: -0.1700
Data Index: 4291086 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19