Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2070. Min Range: -8.2070
Max Act: 8.2070. Min Act: -0.1700
Data Index: 4682460 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2070. Min Range: -8.2070
Max Act: 8.0820. Min Act: -0.1700
Data Index: 2856801 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2070. Min Range: -8.2070
Max Act: 8.0195. Min Act: -0.1700
Data Index: 2427256 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.6758. Min Act: -0.1700
Data Index: 8351177 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.7070. Min Act: -0.1700
Data Index: 7426754 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.7070. Min Act: -0.1700
Data Index: 7140963 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.6758. Min Act: -0.1700
Data Index: 61795 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.6445. Min Act: -0.1700
Data Index: 7823581 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.6445. Min Act: -0.1700
Data Index: 3625628 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.6445. Min Act: -0.1700
Data Index: 8368625 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.6758. Min Act: -0.1700
Data Index: 5405102 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.6445. Min Act: -0.1700
Data Index: 530386 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.6445. Min Act: -0.1700
Data Index: 8315331 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.6133. Min Act: -0.1700
Data Index: 8408155 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.6133. Min Act: -0.1700
Data Index: 32172 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.5508. Min Act: -0.1700
Data Index: 7666419 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.5195. Min Act: -0.1700
Data Index: 805419 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.5195. Min Act: -0.1700
Data Index: 3165044 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.5195. Min Act: -0.1700
Data Index: 2569098 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2070. Min Range: -8.2070
Max Act: 7.4883. Min Act: -0.1700
Data Index: 5855291 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19