Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.3943. Min Act: -0.1700
Data Index: 1134258 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.3318. Min Act: -0.1700
Data Index: 2941867 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.3318. Min Act: -0.1700
Data Index: 2672514 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.2068. Min Act: -0.1700
Data Index: 7807348 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.2068. Min Act: -0.1700
Data Index: 8354504 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.2381. Min Act: -0.1700
Data Index: 2058086 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.2068. Min Act: -0.1700
Data Index: 4667615 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.1756. Min Act: -0.1700
Data Index: 181092 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.2068. Min Act: -0.1700
Data Index: 3625468 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.1756. Min Act: -0.1700
Data Index: 1593769 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.1443. Min Act: -0.1700
Data Index: 2053844 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.1756. Min Act: -0.1700
Data Index: 7569579 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.2068. Min Act: -0.1700
Data Index: 4230271 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.1756. Min Act: -0.1700
Data Index: 8624254 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.1756. Min Act: -0.1700
Data Index: 6358688 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.1756. Min Act: -0.1700
Data Index: 4044881 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.1443. Min Act: -0.1700
Data Index: 7642534 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.1443. Min Act: -0.1700
Data Index: 7784312 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.1443. Min Act: -0.1700
Data Index: 726699 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3943. Min Range: -5.3943
Max Act: 5.1131. Min Act: -0.1700
Data Index: 3424788 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19