Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3342 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.4479. Min Act: -0.1700
Data Index: 28041 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.3854. Min Act: -0.1700
Data Index: 4627631 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.3541. Min Act: -0.1700
Data Index: 8376884 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.2916. Min Act: -0.1700
Data Index: 258448 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.2604. Min Act: -0.1700
Data Index: 5164506 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.2604. Min Act: -0.1700
Data Index: 8622288 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.2604. Min Act: -0.1700
Data Index: 2908160 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.2291. Min Act: -0.1700
Data Index: 1302270 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.2291. Min Act: -0.1700
Data Index: 906677 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.1979. Min Act: -0.1700
Data Index: 1835791 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.1979. Min Act: -0.1700
Data Index: 6633333 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.1979. Min Act: -0.1700
Data Index: 5298486 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.1979. Min Act: -0.1700
Data Index: 5976587 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.1979. Min Act: -0.1700
Data Index: 7399138 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.1666. Min Act: -0.1700
Data Index: 1950343 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.1666. Min Act: -0.1700
Data Index: 4070415 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.1354. Min Act: -0.1700
Data Index: 884578 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.1354. Min Act: -0.1700
Data Index: 8274424 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.1354. Min Act: -0.1700
Data Index: 4813653 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4479. Min Range: -5.4479
Max Act: 5.1354. Min Act: -0.1700
Data Index: 2560044 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19