Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.4809. Min Act: -0.1700
Data Index: 3641982 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.4809. Min Act: -0.1700
Data Index: 3144285 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.3712. Min Act: -0.1700
Data Index: 3612828 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.3398. Min Act: -0.1700
Data Index: 8190924 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.3241. Min Act: -0.1700
Data Index: 4144042 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.3241. Min Act: -0.1700
Data Index: 7491923 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.2142. Min Act: -0.1700
Data Index: 6472213 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1985. Min Act: -0.1700
Data Index: 8725027 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1985. Min Act: -0.1700
Data Index: 5410175 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1985. Min Act: -0.1700
Data Index: 947114 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1827. Min Act: -0.1700
Data Index: 3323263 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1827. Min Act: -0.1700
Data Index: 3398994 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1670. Min Act: -0.1700
Data Index: 3784004 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1827. Min Act: -0.1700
Data Index: 8431857 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1513. Min Act: -0.1700
Data Index: 205672 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1513. Min Act: -0.1700
Data Index: 6134088 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1355. Min Act: -0.1700
Data Index: 7277077 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1513. Min Act: -0.1700
Data Index: 5381128 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1355. Min Act: -0.1700
Data Index: 8496770 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4809. Min Range: -3.4809
Max Act: 3.1513. Min Act: -0.1700
Data Index: 8016613 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19