Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2193. Min Range: -4.2193
Max Act: 4.2193. Min Act: -0.1700
Data Index: 2334576 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.8441. Min Act: -0.1700
Data Index: 1282609 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.7503. Min Act: -0.1700
Data Index: 7309629 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.7190. Min Act: -0.1700
Data Index: 1160147 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.6565. Min Act: -0.1700
Data Index: 5012919 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.5939. Min Act: -0.1700
Data Index: 2255225 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.5939. Min Act: -0.1700
Data Index: 4928815 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.5782. Min Act: -0.1700
Data Index: 4932879 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.5782. Min Act: -0.1700
Data Index: 6860331 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.5626. Min Act: -0.1700
Data Index: 3039964 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.5312. Min Act: -0.1700
Data Index: 2165120 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.5312. Min Act: -0.1700
Data Index: 5575706 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.5156. Min Act: -0.1700
Data Index: 1915161 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.4999. Min Act: -0.1700
Data Index: 2159208 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.4999. Min Act: -0.1700
Data Index: 3565980 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.5156. Min Act: -0.1700
Data Index: 6458440 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.4843. Min Act: -0.1700
Data Index: 5009455 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.4843. Min Act: -0.1700
Data Index: 1940233 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.4999. Min Act: -0.1700
Data Index: 1929041 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2193. Min Range: -4.2193
Max Act: 3.5156. Min Act: -0.1700
Data Index: 6553433 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19