Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2753 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.3109. Min Act: -0.1700
Data Index: 8083836 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.2484. Min Act: -0.1700
Data Index: 653045 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.1859. Min Act: -0.1700
Data Index: 6432916 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.1859. Min Act: -0.1700
Data Index: 1661621 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.1547. Min Act: -0.1700
Data Index: 6025329 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.1234. Min Act: -0.1700
Data Index: 1065140 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.1234. Min Act: -0.1700
Data Index: 6554536 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.1234. Min Act: -0.1700
Data Index: 5124636 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0609. Min Act: -0.1700
Data Index: 6902228 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.1234. Min Act: -0.1700
Data Index: 4070588 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.1234. Min Act: -0.1700
Data Index: 4691821 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0609. Min Act: -0.1700
Data Index: 4630028 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0922. Min Act: -0.1700
Data Index: 1989962 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0922. Min Act: -0.1700
Data Index: 969566 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0922. Min Act: -0.1700
Data Index: 3972649 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0922. Min Act: -0.1700
Data Index: 6375960 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0609. Min Act: -0.1700
Data Index: 1007513 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0922. Min Act: -0.1700
Data Index: 2681999 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0609. Min Act: -0.1700
Data Index: 5290615 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0609. Min Act: -0.1700
Data Index: 5804881 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19