Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 799 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.3897. Min Act: -0.1700
Data Index: 3250398 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.3897. Min Act: -0.1700
Data Index: 8089367 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.2960. Min Act: -0.1700
Data Index: 8089370 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.2647. Min Act: -0.1700
Data Index: 5088827 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.2647. Min Act: -0.1700
Data Index: 6480353 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.2335. Min Act: -0.1700
Data Index: 2708119 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.2335. Min Act: -0.1700
Data Index: 4999840 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.2022. Min Act: -0.1700
Data Index: 3560021 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.2022. Min Act: -0.1700
Data Index: 1055689 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.1397. Min Act: -0.1700
Data Index: 3409735 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.2022. Min Act: -0.1700
Data Index: 2583203 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.1710. Min Act: -0.1700
Data Index: 208470 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.2022. Min Act: -0.1700
Data Index: 3064194 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.1710. Min Act: -0.1700
Data Index: 2583200 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.2022. Min Act: -0.1700
Data Index: 6484063 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.1397. Min Act: -0.1700
Data Index: 1081979 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.1710. Min Act: -0.1700
Data Index: 3263794 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.1397. Min Act: -0.1700
Data Index: 2190766 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.1085. Min Act: -0.1700
Data Index: 7049271 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3897. Min Range: -4.3897
Max Act: 4.1085. Min Act: -0.1700
Data Index: 2852603 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19