Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4444 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0569. Min Range: -7.0569
Max Act: 7.0569. Min Act: -0.1700
Data Index: 7001157 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.9944. Min Act: -0.1700
Data Index: 451713 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.9944. Min Act: -0.1700
Data Index: 3329908 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.9006. Min Act: -0.1700
Data Index: 245883 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.7756. Min Act: -0.1700
Data Index: 7275567 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.7444. Min Act: -0.1700
Data Index: 3844386 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.7444. Min Act: -0.1700
Data Index: 5004124 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.7444. Min Act: -0.1700
Data Index: 1477940 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.7131. Min Act: -0.1700
Data Index: 1760727 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.7131. Min Act: -0.1700
Data Index: 8674572 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.7444. Min Act: -0.1700
Data Index: 8625426 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.7131. Min Act: -0.1700
Data Index: 1791028 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.7444. Min Act: -0.1700
Data Index: 6010845 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.6819. Min Act: -0.1700
Data Index: 196421 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.6819. Min Act: -0.1700
Data Index: 3599727 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.6819. Min Act: -0.1700
Data Index: 4691828 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.6506. Min Act: -0.1700
Data Index: 7870238 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.6194. Min Act: -0.1700
Data Index: 4650018 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.6194. Min Act: -0.1700
Data Index: 2512763 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0569. Min Range: -7.0569
Max Act: 6.6194. Min Act: -0.1700
Data Index: 6930504 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19