Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3708 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.1216. Min Act: -0.1700
Data Index: 8260135 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.1049. Min Act: -0.1700
Data Index: 1975223 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0881. Min Act: -0.1700
Data Index: 7474019 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0377. Min Act: -0.1700
Data Index: 4416231 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0546. Min Act: -0.1700
Data Index: 940137 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0209. Min Act: -0.1700
Data Index: 3076204 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0546. Min Act: -0.1700
Data Index: 8206328 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0209. Min Act: -0.1700
Data Index: 669857 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0377. Min Act: -0.1700
Data Index: 1055805 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0209. Min Act: -0.1700
Data Index: 4664011 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0040. Min Act: -0.1700
Data Index: 685776 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0209. Min Act: -0.1700
Data Index: 8469425 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0209. Min Act: -0.1700
Data Index: 5860964 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0040. Min Act: -0.1700
Data Index: 8566091 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0040. Min Act: -0.1700
Data Index: 1448935 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0040. Min Act: -0.1700
Data Index: 2854428 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1216. Min Range: -2.1216
Max Act: 2.0209. Min Act: -0.1697
Data Index: 4792124 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1216. Min Range: -2.1216
Max Act: 1.9871. Min Act: -0.1700
Data Index: 2740414 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1216. Min Range: -2.1216
Max Act: 1.9871. Min Act: -0.1700
Data Index: 4476481 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1216. Min Range: -2.1216
Max Act: 1.9871. Min Act: -0.1700
Data Index: 4529134 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19