Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4970. Min Act: -0.1700
Data Index: 2948082 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4883. Min Act: -0.1700
Data Index: 7309036 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4531. Min Act: -0.1700
Data Index: 2960443 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4355. Min Act: -0.1700
Data Index: 2960444 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4355. Min Act: -0.1700
Data Index: 5413196 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4355. Min Act: -0.1700
Data Index: 3417644 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4355. Min Act: -0.1700
Data Index: 6859432 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4267. Min Act: -0.1700
Data Index: 5865764 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4091. Min Act: -0.1700
Data Index: 4024462 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4091. Min Act: -0.1700
Data Index: 6363441 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4091. Min Act: -0.1700
Data Index: 6363442 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4091. Min Act: -0.1700
Data Index: 6154355 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4091. Min Act: -0.1700
Data Index: 3087454 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4003. Min Act: -0.1700
Data Index: 1740227 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4003. Min Act: -0.1700
Data Index: 1247495 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.4091. Min Act: -0.1700
Data Index: 5040369 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.3915. Min Act: -0.1700
Data Index: 915935 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.3827. Min Act: -0.1700
Data Index: 7554798 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.3915. Min Act: -0.1700
Data Index: 8693003 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4970. Min Range: -1.4970
Max Act: 1.3915. Min Act: -0.1695
Data Index: 6363440 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19