Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4139. Min Range: -7.4139
Max Act: 7.4139. Min Act: -0.1700
Data Index: 292523 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4139. Min Range: -7.4139
Max Act: 7.3202. Min Act: -0.1700
Data Index: 737177 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4139. Min Range: -7.4139
Max Act: 7.3202. Min Act: -0.1700
Data Index: 285456 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4139. Min Range: -7.4139
Max Act: 7.3202. Min Act: -0.1700
Data Index: 8016301 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4139. Min Range: -7.4139
Max Act: 7.2264. Min Act: -0.1700
Data Index: 3742486 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4139. Min Range: -7.4139
Max Act: 7.1952. Min Act: -0.1700
Data Index: 7573798 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4139. Min Range: -7.4139
Max Act: 7.2264. Min Act: -0.1700
Data Index: 7426491 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4139. Min Range: -7.4139
Max Act: 7.0702. Min Act: -0.1700
Data Index: 626935 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4139. Min Range: -7.4139
Max Act: 7.0077. Min Act: -0.1700
Data Index: 3709856 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4139. Min Range: -7.4139
Max Act: 6.9764. Min Act: -0.1700
Data Index: 2432107 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4139. Min Range: -7.4139
Max Act: 7.0077. Min Act: -0.1700
Data Index: 8424052 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4139. Min Range: -7.4139
Max Act: 6.8827. Min Act: -0.1700
Data Index: 8061699 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4139. Min Range: -7.4139
Max Act: 6.8514. Min Act: -0.1700
Data Index: 5187238 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4139. Min Range: -7.4139
Max Act: 6.8514. Min Act: -0.1700
Data Index: 7569146 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4139. Min Range: -7.4139
Max Act: 6.8827. Min Act: -0.1700
Data Index: 6289758 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4139. Min Range: -7.4139
Max Act: 6.8202. Min Act: -0.1700
Data Index: 2586664 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4139. Min Range: -7.4139
Max Act: 6.8202. Min Act: -0.1700
Data Index: 3064578 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4139. Min Range: -7.4139
Max Act: 6.8202. Min Act: -0.1700
Data Index: 1573293 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4139. Min Range: -7.4139
Max Act: 6.7889. Min Act: -0.1700
Data Index: 7981442 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4139. Min Range: -7.4139
Max Act: 6.7889. Min Act: -0.1700
Data Index: 5333435 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19