Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 590 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1539. Min Range: -7.1539
Max Act: 7.1539. Min Act: -0.1700
Data Index: 3671913 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1539. Min Range: -7.1539
Max Act: 6.2164. Min Act: -0.1700
Data Index: 3773745 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1539. Min Range: -7.1539
Max Act: 6.1227. Min Act: -0.1700
Data Index: 7573510 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.9664. Min Act: -0.1700
Data Index: 7735050 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.9664. Min Act: -0.1700
Data Index: 6916728 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.9664. Min Act: -0.1700
Data Index: 2750041 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.9664. Min Act: -0.1700
Data Index: 2492178 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.9039. Min Act: -0.1700
Data Index: 7805265 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.9352. Min Act: -0.1700
Data Index: 3245296 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.9352. Min Act: -0.1700
Data Index: 434072 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.8727. Min Act: -0.1700
Data Index: 8547054 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.8727. Min Act: -0.1700
Data Index: 473206 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.8727. Min Act: -0.1700
Data Index: 6959312 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.8414. Min Act: -0.1700
Data Index: 7346577 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.8727. Min Act: -0.1700
Data Index: 562192 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.8727. Min Act: -0.1700
Data Index: 4521042 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.8727. Min Act: -0.1700
Data Index: 4877035 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.8414. Min Act: -0.1700
Data Index: 4722015 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.8102. Min Act: -0.1700
Data Index: 8067480 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1539. Min Range: -7.1539
Max Act: 5.8102. Min Act: -0.1700
Data Index: 6578124 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19