Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1794 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.7210. Min Act: -0.1700
Data Index: 7430870 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.6777. Min Act: -0.1700
Data Index: 5826272 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.6690. Min Act: -0.1700
Data Index: 7585640 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.6429. Min Act: -0.1700
Data Index: 7184096 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.6429. Min Act: -0.1700
Data Index: 3731826 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.6429. Min Act: -0.1700
Data Index: 1745000 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.6342. Min Act: -0.1700
Data Index: 740522 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.6255. Min Act: -0.1700
Data Index: 6367548 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.6080. Min Act: -0.1700
Data Index: 2277902 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.6080. Min Act: -0.1700
Data Index: 629386 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.6080. Min Act: -0.1700
Data Index: 5987084 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.5993. Min Act: -0.1700
Data Index: 3132099 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.5818. Min Act: -0.1700
Data Index: 5550444 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.5731. Min Act: -0.1700
Data Index: 7430867 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.5731. Min Act: -0.1700
Data Index: 3438454 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.5556. Min Act: -0.1700
Data Index: 3567801 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.5731. Min Act: -0.1700
Data Index: 8225581 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.5818. Min Act: -0.1700
Data Index: 2214225 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.5731. Min Act: -0.1700
Data Index: 789040 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7210. Min Range: -1.7210
Max Act: 1.5643. Min Act: -0.1700
Data Index: 1100617 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19