Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5485. Min Range: -8.5485
Max Act: 8.5485. Min Act: -0.1700
Data Index: 8711325 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.8923. Min Act: -0.1700
Data Index: 1954479 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.8298. Min Act: -0.1700
Data Index: 6334983 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.7360. Min Act: -0.1700
Data Index: 673197 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.4860. Min Act: -0.1700
Data Index: 6319170 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.4548. Min Act: -0.1700
Data Index: 5815283 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.3610. Min Act: -0.1700
Data Index: 5129768 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.3298. Min Act: -0.1700
Data Index: 2579113 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.3298. Min Act: -0.1700
Data Index: 5337952 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.2673. Min Act: -0.1700
Data Index: 8301506 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.2673. Min Act: -0.1700
Data Index: 6318722 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.2048. Min Act: -0.1700
Data Index: 754327 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.2048. Min Act: -0.1700
Data Index: 687078 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.2048. Min Act: -0.1700
Data Index: 4461700 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.2048. Min Act: -0.1700
Data Index: 3424441 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.2048. Min Act: -0.1700
Data Index: 499624 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.2048. Min Act: -0.1700
Data Index: 4117001 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.1735. Min Act: -0.1700
Data Index: 2801963 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.1735. Min Act: -0.1700
Data Index: 4632700 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5485. Min Range: -8.5485
Max Act: 7.2048. Min Act: -0.1700
Data Index: 1262308 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19