Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1570 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.7979. Min Act: -0.1700
Data Index: 2291139 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.7042. Min Act: -0.1700
Data Index: 1230379 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.6729. Min Act: -0.1700
Data Index: 3249937 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.6729. Min Act: -0.1700
Data Index: 3469544 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.6104. Min Act: -0.1700
Data Index: 5811939 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.5792. Min Act: -0.1700
Data Index: 4188177 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.5479. Min Act: -0.1700
Data Index: 4332888 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.5479. Min Act: -0.1700
Data Index: 4188178 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.4854. Min Act: -0.1700
Data Index: 7330019 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.5167. Min Act: -0.1700
Data Index: 340799 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.4854. Min Act: -0.1700
Data Index: 8075735 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.4854. Min Act: -0.1700
Data Index: 4521928 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.4854. Min Act: -0.1700
Data Index: 6799508 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.4229. Min Act: -0.1700
Data Index: 1599947 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.4854. Min Act: -0.1700
Data Index: 1927965 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.4542. Min Act: -0.1700
Data Index: 8259532 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.4229. Min Act: -0.1700
Data Index: 4658366 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.4542. Min Act: -0.1700
Data Index: 3114175 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.4229. Min Act: -0.1700
Data Index: 2164078 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7979. Min Range: -4.7979
Max Act: 4.4229. Min Act: -0.1700
Data Index: 7268868 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19