Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1204 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.3139. Min Act: -0.1700
Data Index: 6813910 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.3304. Min Act: -0.1700
Data Index: 1735547 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.2810. Min Act: -0.1700
Data Index: 1901682 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.2645. Min Act: -0.1700
Data Index: 6093266 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.2645. Min Act: -0.1700
Data Index: 2058662 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.2315. Min Act: -0.1700
Data Index: 4997471 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.2315. Min Act: -0.1700
Data Index: 672380 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.2480. Min Act: -0.1700
Data Index: 8322715 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.2149. Min Act: -0.1700
Data Index: 2369482 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.1817. Min Act: -0.1700
Data Index: 3999244 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.1983. Min Act: -0.1700
Data Index: 8518755 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.1983. Min Act: -0.1700
Data Index: 602346 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.1817. Min Act: -0.1700
Data Index: 4917538 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.1651. Min Act: -0.1700
Data Index: 6890048 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.1817. Min Act: -0.1700
Data Index: 5074080 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.1484. Min Act: -0.1700
Data Index: 7703336 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.1651. Min Act: -0.1700
Data Index: 4442922 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.1817. Min Act: -0.1700
Data Index: 8324273 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.1484. Min Act: -0.1700
Data Index: 6970096 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3304. Min Range: -2.3304
Max Act: 2.1651. Min Act: -0.1700
Data Index: 2705440 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19