Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2315 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.4544. Min Act: -0.1700
Data Index: 993982 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.3294. Min Act: -0.1700
Data Index: 1752999 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.2669. Min Act: -0.1700
Data Index: 4731369 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.2356. Min Act: -0.1700
Data Index: 2859161 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.1731. Min Act: -0.1700
Data Index: 5029899 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.1419. Min Act: -0.1700
Data Index: 3997291 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.1419. Min Act: -0.1700
Data Index: 5974341 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.1106. Min Act: -0.1700
Data Index: 7522350 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.1106. Min Act: -0.1700
Data Index: 8637024 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.1106. Min Act: -0.1700
Data Index: 7468634 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0793. Min Act: -0.1700
Data Index: 6381527 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0793. Min Act: -0.1700
Data Index: 1295496 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0793. Min Act: -0.1700
Data Index: 7455603 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0793. Min Act: -0.1700
Data Index: 5792592 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0793. Min Act: -0.1700
Data Index: 5730177 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0793. Min Act: -0.1700
Data Index: 7287223 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0793. Min Act: -0.1700
Data Index: 6723016 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0481. Min Act: -0.1700
Data Index: 2937428 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0481. Min Act: -0.1700
Data Index: 303068 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4544. Min Range: -4.4544
Max Act: 4.0481. Min Act: -0.1700
Data Index: 5068758 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19