Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.6214. Min Act: -0.1700
Data Index: 3269533 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.5901. Min Act: -0.1700
Data Index: 80909 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.5901. Min Act: -0.1700
Data Index: 4064765 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.4651. Min Act: -0.1700
Data Index: 3252133 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.4651. Min Act: -0.1700
Data Index: 3766484 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.4651. Min Act: -0.1700
Data Index: 3114258 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.4338. Min Act: -0.1700
Data Index: 5934643 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.4338. Min Act: -0.1700
Data Index: 5934651 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.4338. Min Act: -0.1700
Data Index: 6058869 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.4026. Min Act: -0.1700
Data Index: 2228915 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.4338. Min Act: -0.1700
Data Index: 6311790 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.3713. Min Act: -0.1700
Data Index: 5793715 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.3713. Min Act: -0.1700
Data Index: 8750854 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.3401. Min Act: -0.1700
Data Index: 7768416 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.3713. Min Act: -0.1700
Data Index: 2156429 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.3713. Min Act: -0.1700
Data Index: 1069628 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.3713. Min Act: -0.1700
Data Index: 5363299 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.3088. Min Act: -0.1700
Data Index: 5681148 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.3088. Min Act: -0.1700
Data Index: 1864620 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6214. Min Range: -4.6214
Max Act: 4.3088. Min Act: -0.1700
Data Index: 6828735 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19