Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 774 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.5572. Min Act: -0.1700
Data Index: 8735136 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.5572. Min Act: -0.1700
Data Index: 2027911 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.5103. Min Act: -0.1700
Data Index: 7661382 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.5103. Min Act: -0.1700
Data Index: 3878030 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4946. Min Act: -0.1700
Data Index: 640151 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4946. Min Act: -0.1700
Data Index: 6862987 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4789. Min Act: -0.1700
Data Index: 4784076 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4633. Min Act: -0.1700
Data Index: 5058790 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4789. Min Act: -0.1700
Data Index: 7606898 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4476. Min Act: -0.1700
Data Index: 7568765 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4476. Min Act: -0.1700
Data Index: 8287083 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4163. Min Act: -0.1700
Data Index: 4255664 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4476. Min Act: -0.1700
Data Index: 1892039 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4319. Min Act: -0.1700
Data Index: 5209481 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4163. Min Act: -0.1700
Data Index: 1869982 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4319. Min Act: -0.1700
Data Index: 1110362 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4163. Min Act: -0.1700
Data Index: 7905134 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4163. Min Act: -0.1700
Data Index: 1128145 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4163. Min Act: -0.1700
Data Index: 3799788 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5572. Min Range: -3.5572
Max Act: 3.4006. Min Act: -0.1700
Data Index: 4587865 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19