Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4095 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.3040. Min Act: -0.1700
Data Index: 8655810 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.2415. Min Act: -0.1700
Data Index: 1957976 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.2102. Min Act: -0.1700
Data Index: 724827 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.1477. Min Act: -0.1700
Data Index: 1918698 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.1790. Min Act: -0.1700
Data Index: 198449 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.1165. Min Act: -0.1700
Data Index: 8583118 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.0852. Min Act: -0.1700
Data Index: 196991 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.1165. Min Act: -0.1700
Data Index: 2267459 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.1165. Min Act: -0.1700
Data Index: 6830117 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.1165. Min Act: -0.1700
Data Index: 8312231 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.0852. Min Act: -0.1700
Data Index: 7233573 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.1165. Min Act: -0.1700
Data Index: 1348265 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.1165. Min Act: -0.1700
Data Index: 8781294 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.0852. Min Act: -0.1700
Data Index: 137505 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.0852. Min Act: -0.1700
Data Index: 7915941 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.0540. Min Act: -0.1700
Data Index: 5478556 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.0852. Min Act: -0.1700
Data Index: 2634169 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.0540. Min Act: -0.1700
Data Index: 5150664 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.0540. Min Act: -0.1700
Data Index: 1796434 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3040. Min Range: -5.3040
Max Act: 5.0540. Min Act: -0.1700
Data Index: 2304003 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19