Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1667 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.8674. Min Act: -0.1700
Data Index: 372609 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.7424. Min Act: -0.1700
Data Index: 1968440 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.5549. Min Act: -0.1700
Data Index: 4091857 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.4299. Min Act: -0.1700
Data Index: 6632811 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.4299. Min Act: -0.1700
Data Index: 2725479 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.4299. Min Act: -0.1700
Data Index: 7548496 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.3049. Min Act: -0.1700
Data Index: 750473 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.2424. Min Act: -0.1700
Data Index: 992776 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.3049. Min Act: -0.1700
Data Index: 4792199 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.2424. Min Act: -0.1700
Data Index: 1992729 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.2424. Min Act: -0.1700
Data Index: 8282944 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.2424. Min Act: -0.1700
Data Index: 8722685 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.1799. Min Act: -0.1700
Data Index: 2247807 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.1799. Min Act: -0.1700
Data Index: 880237 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.1174. Min Act: -0.1700
Data Index: 448183 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.1174. Min Act: -0.1700
Data Index: 4592362 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.0861. Min Act: -0.1700
Data Index: 5640209 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8674. Min Range: -8.8674
Max Act: 7.9924. Min Act: -0.1700
Data Index: 6834972 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8674. Min Range: -8.8674
Max Act: 8.0549. Min Act: -0.1700
Data Index: 8187153 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8674. Min Range: -8.8674
Max Act: 7.9924. Min Act: -0.1700
Data Index: 1637226 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19