Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1246 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.7672. Min Act: -0.1700
Data Index: 1888967 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.7985. Min Act: -0.1700
Data Index: 4181715 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.7672. Min Act: -0.1700
Data Index: 5421857 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6734. Min Act: -0.1700
Data Index: 7565717 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.7046. Min Act: -0.1700
Data Index: 2909604 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.7046. Min Act: -0.1700
Data Index: 5362284 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.7359. Min Act: -0.1700
Data Index: 879125 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6421. Min Act: -0.1700
Data Index: 6125363 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.7046. Min Act: -0.1700
Data Index: 6253521 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6421. Min Act: -0.1700
Data Index: 7064755 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6421. Min Act: -0.1700
Data Index: 792012 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6421. Min Act: -0.1700
Data Index: 2907680 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6108. Min Act: -0.1700
Data Index: 3685203 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6421. Min Act: -0.1700
Data Index: 3453701 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6108. Min Act: -0.1700
Data Index: 8548349 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6421. Min Act: -0.1700
Data Index: 8056181 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6421. Min Act: -0.1700
Data Index: 5698656 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6421. Min Act: -0.1700
Data Index: 414702 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6108. Min Act: -0.1700
Data Index: 565236 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7985. Min Range: -3.7985
Max Act: 3.6108. Min Act: -0.1700
Data Index: 5393690 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19