Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4114. Min Range: -8.4114
Max Act: 8.4114. Min Act: -0.1700
Data Index: 8786041 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4114. Min Range: -8.4114
Max Act: 8.1614. Min Act: -0.1700
Data Index: 7273880 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4114. Min Range: -8.4114
Max Act: 8.0364. Min Act: -0.1700
Data Index: 8746984 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.9739. Min Act: -0.1700
Data Index: 7749286 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.9114. Min Act: -0.1700
Data Index: 7528060 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.8489. Min Act: -0.1700
Data Index: 663249 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.7864. Min Act: -0.1700
Data Index: 3864776 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.6614. Min Act: -0.1700
Data Index: 6618690 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.5989. Min Act: -0.1700
Data Index: 1894720 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.5677. Min Act: -0.1700
Data Index: 2212820 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.5364. Min Act: -0.1700
Data Index: 8359533 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.5364. Min Act: -0.1700
Data Index: 4089734 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.5052. Min Act: -0.1700
Data Index: 7341798 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.4739. Min Act: -0.1700
Data Index: 4670232 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.4739. Min Act: -0.1700
Data Index: 7999008 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.5052. Min Act: -0.1700
Data Index: 1360712 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.5052. Min Act: -0.1700
Data Index: 1643696 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.4739. Min Act: -0.1700
Data Index: 7430359 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.4427. Min Act: -0.1700
Data Index: 23097 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4114. Min Range: -8.4114
Max Act: 7.4427. Min Act: -0.1700
Data Index: 3466121 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19