Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.8113. Min Act: -0.1700
Data Index: 4847697 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.8113. Min Act: -0.1700
Data Index: 7787352 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.7176. Min Act: -0.1700
Data Index: 4240668 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.6863. Min Act: -0.1700
Data Index: 4690880 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.6551. Min Act: -0.1700
Data Index: 800904 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.6238. Min Act: -0.1700
Data Index: 6339904 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.6238. Min Act: -0.1700
Data Index: 3599923 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.6238. Min Act: -0.1700
Data Index: 1958325 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.6238. Min Act: -0.1700
Data Index: 2866053 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5613. Min Act: -0.1700
Data Index: 1622802 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5926. Min Act: -0.1700
Data Index: 4307449 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5926. Min Act: -0.1700
Data Index: 5021374 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5613. Min Act: -0.1700
Data Index: 6823232 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5301. Min Act: -0.1700
Data Index: 5547536 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5613. Min Act: -0.1700
Data Index: 1273601 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.4988. Min Act: -0.1700
Data Index: 4361540 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.4676. Min Act: -0.1700
Data Index: 3414181 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.4676. Min Act: -0.1700
Data Index: 6751373 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.4988. Min Act: -0.1700
Data Index: 4476679 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.4676. Min Act: -0.1700
Data Index: 3036271 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19