Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4056 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.6380. Min Act: -0.1700
Data Index: 5262011 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.6067. Min Act: -0.1700
Data Index: 8771452 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.5755. Min Act: -0.1700
Data Index: 6712948 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.4817. Min Act: -0.1700
Data Index: 4135031 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.5130. Min Act: -0.1700
Data Index: 6716542 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.5130. Min Act: -0.1700
Data Index: 97886 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.4817. Min Act: -0.1700
Data Index: 6352577 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.5130. Min Act: -0.1700
Data Index: 5071595 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.4192. Min Act: -0.1700
Data Index: 2330362 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.4505. Min Act: -0.1700
Data Index: 8712464 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.4192. Min Act: -0.1700
Data Index: 2799600 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.4192. Min Act: -0.1700
Data Index: 679970 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.3880. Min Act: -0.1700
Data Index: 1441727 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.3880. Min Act: -0.1700
Data Index: 3154378 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.4192. Min Act: -0.1700
Data Index: 701056 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.3880. Min Act: -0.1700
Data Index: 4714825 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.3567. Min Act: -0.1700
Data Index: 7406927 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.4192. Min Act: -0.1700
Data Index: 675437 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.3880. Min Act: -0.1700
Data Index: 675436 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6380. Min Range: -4.6380
Max Act: 4.3880. Min Act: -0.1700
Data Index: 5383900 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19