Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 865 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0624. Min Range: -2.0624
Max Act: 2.0624. Min Act: -0.1700
Data Index: 1049059 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0624. Min Range: -2.0624
Max Act: 2.0288. Min Act: -0.1699
Data Index: 6099372 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9950. Min Act: -0.1697
Data Index: 6224598 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9950. Min Act: -0.1700
Data Index: 4803355 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9611. Min Act: -0.1700
Data Index: 8192420 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9442. Min Act: -0.1698
Data Index: 2091228 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9611. Min Act: -0.1698
Data Index: 8295835 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9611. Min Act: -0.1700
Data Index: 769178 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9442. Min Act: -0.1696
Data Index: 2091227 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9442. Min Act: -0.1700
Data Index: 3463765 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9442. Min Act: -0.1700
Data Index: 3047071 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9442. Min Act: -0.1698
Data Index: 1745317 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9442. Min Act: -0.1700
Data Index: 3035667 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9442. Min Act: -0.1700
Data Index: 1668333 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9442. Min Act: -0.1689
Data Index: 739666 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9442. Min Act: -0.1581
Data Index: 4493821 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9442. Min Act: -0.1700
Data Index: 183002 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9272. Min Act: -0.1700
Data Index: 193499 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9101. Min Act: -0.1692
Data Index: 758346 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0624. Min Range: -2.0624
Max Act: 1.9272. Min Act: -0.1700
Data Index: 2743408 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19