Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4384 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.6126. Min Act: -0.1700
Data Index: 7118524 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.6438. Min Act: -0.1700
Data Index: 1305153 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.3938. Min Act: -0.1700
Data Index: 3909909 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.3626. Min Act: -0.1700
Data Index: 3592816 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.3313. Min Act: -0.1700
Data Index: 6851341 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.2688. Min Act: -0.1700
Data Index: 4969655 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.2688. Min Act: -0.1700
Data Index: 708064 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.2688. Min Act: -0.1700
Data Index: 2327055 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.2063. Min Act: -0.1700
Data Index: 133372 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.2063. Min Act: -0.1700
Data Index: 5516447 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.1750. Min Act: -0.1700
Data Index: 8372236 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.1750. Min Act: -0.1700
Data Index: 1604963 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.2063. Min Act: -0.1700
Data Index: 7131057 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.1750. Min Act: -0.1700
Data Index: 6692085 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.1438. Min Act: -0.1700
Data Index: 6701664 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.1438. Min Act: -0.1700
Data Index: 816323 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.1438. Min Act: -0.1700
Data Index: 5490396 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.1438. Min Act: -0.1700
Data Index: 5294991 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.1125. Min Act: -0.1700
Data Index: 525373 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6438. Min Range: -4.6438
Max Act: 4.1438. Min Act: -0.1700
Data Index: 3688179 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19