Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2059 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.5427. Min Act: -0.1700
Data Index: 954715 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.5427. Min Act: -0.1700
Data Index: 510842 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.5114. Min Act: -0.1700
Data Index: 5609159 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.5114. Min Act: -0.1700
Data Index: 5091618 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.4489. Min Act: -0.1700
Data Index: 57590 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.4489. Min Act: -0.1700
Data Index: 7163122 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.4177. Min Act: -0.1700
Data Index: 6264885 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.4489. Min Act: -0.1700
Data Index: 7435215 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.3864. Min Act: -0.1700
Data Index: 7573515 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.3864. Min Act: -0.1700
Data Index: 1633224 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.3552. Min Act: -0.1700
Data Index: 1184676 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.3552. Min Act: -0.1700
Data Index: 3540275 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.3239. Min Act: -0.1700
Data Index: 8495027 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.3552. Min Act: -0.1700
Data Index: 1631706 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.3239. Min Act: -0.1700
Data Index: 6225523 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.2614. Min Act: -0.1700
Data Index: 2702711 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.2302. Min Act: -0.1700
Data Index: 4974816 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.2614. Min Act: -0.1700
Data Index: 2113628 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.2927. Min Act: -0.1700
Data Index: 1265635 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5427. Min Range: -5.5427
Max Act: 5.2614. Min Act: -0.1700
Data Index: 5865265 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19