Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2674 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.3676. Min Act: -0.1700
Data Index: 1372189 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.3989. Min Act: -0.1700
Data Index: 8683531 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.3364. Min Act: -0.1700
Data Index: 2653946 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.3051. Min Act: -0.1700
Data Index: 3172001 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.2426. Min Act: -0.1700
Data Index: 1962510 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.2426. Min Act: -0.1700
Data Index: 578206 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.2114. Min Act: -0.1700
Data Index: 8683533 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.2426. Min Act: -0.1700
Data Index: 237169 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.1801. Min Act: -0.1700
Data Index: 1607704 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.1489. Min Act: -0.1700
Data Index: 8741709 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.1489. Min Act: -0.1700
Data Index: 2233483 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.1176. Min Act: -0.1700
Data Index: 2015770 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.1176. Min Act: -0.1700
Data Index: 5111931 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.1176. Min Act: -0.1700
Data Index: 5111935 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.1176. Min Act: -0.1700
Data Index: 4467016 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.0864. Min Act: -0.1700
Data Index: 360022 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.0864. Min Act: -0.1700
Data Index: 8461419 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.0864. Min Act: -0.1700
Data Index: 6103313 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.0864. Min Act: -0.1700
Data Index: 507376 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3989. Min Range: -5.3989
Max Act: 5.0864. Min Act: -0.1700
Data Index: 6790814 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19