Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2225 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.8552. Min Act: -0.1700
Data Index: 6619893 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.8552. Min Act: -0.1700
Data Index: 1680197 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7916. Min Act: -0.1700
Data Index: 6619894 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.8075. Min Act: -0.1700
Data Index: 6619896 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7916. Min Act: -0.1700
Data Index: 818126 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7756. Min Act: -0.1700
Data Index: 6619895 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7756. Min Act: -0.1700
Data Index: 235143 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7916. Min Act: -0.1700
Data Index: 939894 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7437. Min Act: -0.1700
Data Index: 5374972 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7278. Min Act: -0.1700
Data Index: 1203868 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7437. Min Act: -0.1700
Data Index: 8574562 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7437. Min Act: -0.1700
Data Index: 5520944 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7437. Min Act: -0.1700
Data Index: 4307197 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7278. Min Act: -0.1700
Data Index: 2071774 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7278. Min Act: -0.1700
Data Index: 3012646 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7118. Min Act: -0.1700
Data Index: 6161001 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7118. Min Act: -0.1700
Data Index: 2458252 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7118. Min Act: -0.1700
Data Index: 4899048 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.7118. Min Act: -0.1700
Data Index: 777457 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8552. Min Range: -2.8552
Max Act: 2.6958. Min Act: -0.1700
Data Index: 5123241 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19