Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4804 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3208. Min Range: -7.3208
Max Act: 7.3208. Min Act: -0.1700
Data Index: 4679075 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3208. Min Range: -7.3208
Max Act: 7.1645. Min Act: -0.1700
Data Index: 2885177 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3208. Min Range: -7.3208
Max Act: 7.0083. Min Act: -0.1700
Data Index: 3838415 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3208. Min Range: -7.3208
Max Act: 7.0083. Min Act: -0.1700
Data Index: 950169 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.9458. Min Act: -0.1700
Data Index: 6417716 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.8520. Min Act: -0.1700
Data Index: 7650420 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.8208. Min Act: -0.1700
Data Index: 7531280 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.8208. Min Act: -0.1700
Data Index: 3324455 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.7583. Min Act: -0.1700
Data Index: 4157577 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.6958. Min Act: -0.1700
Data Index: 6939973 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.7270. Min Act: -0.1700
Data Index: 6834945 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.6645. Min Act: -0.1700
Data Index: 1820031 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.6958. Min Act: -0.1700
Data Index: 1168772 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.6333. Min Act: -0.1700
Data Index: 445248 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.6020. Min Act: -0.1700
Data Index: 944912 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.5708. Min Act: -0.1700
Data Index: 6367206 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.5708. Min Act: -0.1700
Data Index: 7073491 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.5708. Min Act: -0.1700
Data Index: 4947430 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.5083. Min Act: -0.1700
Data Index: 2651544 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3208. Min Range: -7.3208
Max Act: 6.5083. Min Act: -0.1700
Data Index: 1728787 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19