Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.4736. Min Act: -0.1700
Data Index: 913758 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.4424. Min Act: -0.1700
Data Index: 7390349 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.4424. Min Act: -0.1700
Data Index: 3566808 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.4111. Min Act: -0.1700
Data Index: 1985858 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.3798. Min Act: -0.1700
Data Index: 2774045 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.3798. Min Act: -0.1700
Data Index: 1983650 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.3798. Min Act: -0.1700
Data Index: 8034297 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.3486. Min Act: -0.1700
Data Index: 1252503 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.3486. Min Act: -0.1700
Data Index: 998478 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.3486. Min Act: -0.1700
Data Index: 6832615 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.3486. Min Act: -0.1698
Data Index: 1070697 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.2861. Min Act: -0.1700
Data Index: 6916369 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.3173. Min Act: -0.1700
Data Index: 2298926 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.3173. Min Act: -0.1700
Data Index: 2087465 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.2861. Min Act: -0.1700
Data Index: 7561588 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.2548. Min Act: -0.1700
Data Index: 1456097 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.3173. Min Act: -0.1700
Data Index: 5757233 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.3173. Min Act: -0.1700
Data Index: 2925756 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.2861. Min Act: -0.1700
Data Index: 3725725 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4736. Min Range: -4.4736
Max Act: 4.2861. Min Act: -0.1700
Data Index: 8709959 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19