Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.2710. Min Act: -0.1700
Data Index: 7835982 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.2553. Min Act: -0.1700
Data Index: 7271991 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.1924. Min Act: -0.1700
Data Index: 6303176 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.1924. Min Act: -0.1700
Data Index: 395407 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.1294. Min Act: -0.1700
Data Index: 6396130 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0822. Min Act: -0.1700
Data Index: 276271 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0979. Min Act: -0.1700
Data Index: 6184827 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0664. Min Act: -0.1700
Data Index: 1113646 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0506. Min Act: -0.1700
Data Index: 59512 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0348. Min Act: -0.1700
Data Index: 4811388 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0506. Min Act: -0.1700
Data Index: 4545578 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0506. Min Act: -0.1700
Data Index: 6676365 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0664. Min Act: -0.1700
Data Index: 1334446 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0506. Min Act: -0.1700
Data Index: 1856091 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0348. Min Act: -0.1700
Data Index: 1684764 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0348. Min Act: -0.1700
Data Index: 8126591 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0190. Min Act: -0.1700
Data Index: 5744382 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0190. Min Act: -0.1700
Data Index: 333730 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0190. Min Act: -0.1700
Data Index: 8048885 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2710. Min Range: -3.2710
Max Act: 3.0032. Min Act: -0.1700
Data Index: 3734710 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19