Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2948 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.8892. Min Act: -0.1700
Data Index: 3848281 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.7330. Min Act: -0.1700
Data Index: 5989500 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.7017. Min Act: -0.1700
Data Index: 7054452 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.7017. Min Act: -0.1700
Data Index: 6028239 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.7330. Min Act: -0.1700
Data Index: 8109837 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.6705. Min Act: -0.1700
Data Index: 238433 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.6705. Min Act: -0.1700
Data Index: 2641469 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.6705. Min Act: -0.1700
Data Index: 1243591 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.6392. Min Act: -0.1700
Data Index: 593008 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.6392. Min Act: -0.1700
Data Index: 6396805 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.6080. Min Act: -0.1700
Data Index: 81216 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.6080. Min Act: -0.1700
Data Index: 8386065 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.5767. Min Act: -0.1700
Data Index: 5693563 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.5767. Min Act: -0.1700
Data Index: 4808039 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.5767. Min Act: -0.1700
Data Index: 4520889 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.5767. Min Act: -0.1700
Data Index: 4510818 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.5767. Min Act: -0.1700
Data Index: 7307940 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.5767. Min Act: -0.1700
Data Index: 3268982 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.5767. Min Act: -0.1700
Data Index: 2816215 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8892. Min Range: -4.8892
Max Act: 4.5767. Min Act: -0.1700
Data Index: 605005 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19