Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3545. Min Range: -7.3545
Max Act: 7.3545. Min Act: -0.1700
Data Index: 1549983 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3545. Min Range: -7.3545
Max Act: 7.0107. Min Act: -0.1700
Data Index: 7989813 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.9482. Min Act: -0.1700
Data Index: 5361096 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.9795. Min Act: -0.1700
Data Index: 1195211 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.8857. Min Act: -0.1700
Data Index: 2266428 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.8545. Min Act: -0.1700
Data Index: 6510602 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.8545. Min Act: -0.1700
Data Index: 4256047 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.8545. Min Act: -0.1700
Data Index: 7116651 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.8232. Min Act: -0.1700
Data Index: 215803 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.8232. Min Act: -0.1700
Data Index: 2340507 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.7920. Min Act: -0.1700
Data Index: 7065555 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.7607. Min Act: -0.1700
Data Index: 4813347 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.8232. Min Act: -0.1700
Data Index: 5782773 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.7607. Min Act: -0.1700
Data Index: 775974 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.7607. Min Act: -0.1700
Data Index: 8544887 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.7607. Min Act: -0.1700
Data Index: 6760109 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.7295. Min Act: -0.1700
Data Index: 7646580 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.7295. Min Act: -0.1700
Data Index: 192507 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.7295. Min Act: -0.1700
Data Index: 7887275 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3545. Min Range: -7.3545
Max Act: 6.7295. Min Act: -0.1700
Data Index: 5219469 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19