Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3080 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.4928. Min Act: -0.1700
Data Index: 3368400 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.4771. Min Act: -0.1700
Data Index: 6983636 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.4301. Min Act: -0.1700
Data Index: 2596469 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.2575. Min Act: -0.1700
Data Index: 5312516 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.2575. Min Act: -0.1700
Data Index: 4871694 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.2732. Min Act: -0.1700
Data Index: 2589230 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.2418. Min Act: -0.1700
Data Index: 3810257 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.2261. Min Act: -0.1700
Data Index: 4731963 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.2418. Min Act: -0.1700
Data Index: 7435812 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.2261. Min Act: -0.1700
Data Index: 4082228 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.2418. Min Act: -0.1700
Data Index: 8582160 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.2261. Min Act: -0.1700
Data Index: 6639096 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.2103. Min Act: -0.1700
Data Index: 5835474 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.1946. Min Act: -0.1700
Data Index: 5077957 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.1789. Min Act: -0.1700
Data Index: 3771663 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.1789. Min Act: -0.1700
Data Index: 3089111 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.1632. Min Act: -0.1700
Data Index: 6457752 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.1632. Min Act: -0.1700
Data Index: 350310 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.1632. Min Act: -0.1700
Data Index: 7631237 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4928. Min Range: -3.4928
Max Act: 3.1632. Min Act: -0.1700
Data Index: 999576 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19