Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.2261. Min Act: -0.1700
Data Index: 7645831 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.2084. Min Act: -0.1692
Data Index: 8075097 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.2084. Min Act: -0.1700
Data Index: 4891771 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1996. Min Act: -0.1699
Data Index: 7302141 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1820. Min Act: -0.1696
Data Index: 1709944 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1820. Min Act: -0.1682
Data Index: 3813581 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1820. Min Act: -0.1697
Data Index: 8733982 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1820. Min Act: -0.1683
Data Index: 7182253 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1732. Min Act: -0.1698
Data Index: 2669193 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1644. Min Act: -0.1698
Data Index: 6365586 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1732. Min Act: -0.1699
Data Index: 4322282 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1644. Min Act: -0.1700
Data Index: 6602985 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1644. Min Act: -0.1699
Data Index: 7839500 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1557. Min Act: -0.1699
Data Index: 2186347 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1644. Min Act: -0.1700
Data Index: 4658843 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1644. Min Act: -0.1655
Data Index: 771577 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1644. Min Act: -0.1699
Data Index: 22111 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1644. Min Act: -0.1700
Data Index: 135348 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1557. Min Act: -0.1700
Data Index: 4465433 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2261. Min Range: -1.2261
Max Act: 1.1469. Min Act: -0.1700
Data Index: 541800 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19