Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1255 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4472. Min Range: -6.4472
Max Act: 6.4472. Min Act: -0.1700
Data Index: 3263356 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4472. Min Range: -6.4472
Max Act: 6.2597. Min Act: -0.1700
Data Index: 7615923 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4472. Min Range: -6.4472
Max Act: 6.1034. Min Act: -0.1700
Data Index: 6168563 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4472. Min Range: -6.4472
Max Act: 6.1034. Min Act: -0.1700
Data Index: 2755989 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4472. Min Range: -6.4472
Max Act: 6.1034. Min Act: -0.1700
Data Index: 4146181 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4472. Min Range: -6.4472
Max Act: 6.1034. Min Act: -0.1700
Data Index: 2888984 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4472. Min Range: -6.4472
Max Act: 6.0409. Min Act: -0.1700
Data Index: 1601911 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.9472. Min Act: -0.1700
Data Index: 4143324 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.8847. Min Act: -0.1700
Data Index: 5723059 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.8534. Min Act: -0.1700
Data Index: 8661892 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.8222. Min Act: -0.1700
Data Index: 4071208 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.8534. Min Act: -0.1700
Data Index: 7792118 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.8222. Min Act: -0.1700
Data Index: 2086588 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.8222. Min Act: -0.1700
Data Index: 545791 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.8222. Min Act: -0.1700
Data Index: 1395023 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.8222. Min Act: -0.1700
Data Index: 4754469 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.8222. Min Act: -0.1700
Data Index: 7524424 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.7909. Min Act: -0.1700
Data Index: 7741327 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.7909. Min Act: -0.1700
Data Index: 999124 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4472. Min Range: -6.4472
Max Act: 5.7597. Min Act: -0.1700
Data Index: 3168075 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19