Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6240 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5069. Min Range: -7.5069
Max Act: 7.5069. Min Act: -0.1700
Data Index: 6007141 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5069. Min Range: -7.5069
Max Act: 7.3194. Min Act: -0.1700
Data Index: 6437578 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5069. Min Range: -7.5069
Max Act: 7.2569. Min Act: -0.1700
Data Index: 4091277 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5069. Min Range: -7.5069
Max Act: 7.1632. Min Act: -0.1700
Data Index: 6377058 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5069. Min Range: -7.5069
Max Act: 7.1319. Min Act: -0.1700
Data Index: 8596150 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5069. Min Range: -7.5069
Max Act: 7.1319. Min Act: -0.1700
Data Index: 306669 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5069. Min Range: -7.5069
Max Act: 7.1007. Min Act: -0.1700
Data Index: 7923442 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5069. Min Range: -7.5069
Max Act: 7.0694. Min Act: -0.1700
Data Index: 1784063 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5069. Min Range: -7.5069
Max Act: 6.9757. Min Act: -0.1700
Data Index: 1692854 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5069. Min Range: -7.5069
Max Act: 6.9444. Min Act: -0.1700
Data Index: 5263767 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5069. Min Range: -7.5069
Max Act: 6.9757. Min Act: -0.1700
Data Index: 5809560 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5069. Min Range: -7.5069
Max Act: 6.9757. Min Act: -0.1700
Data Index: 8606988 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5069. Min Range: -7.5069
Max Act: 7.0069. Min Act: -0.1700
Data Index: 5622981 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5069. Min Range: -7.5069
Max Act: 6.9444. Min Act: -0.1700
Data Index: 6112899 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5069. Min Range: -7.5069
Max Act: 6.9132. Min Act: -0.1700
Data Index: 6038589 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5069. Min Range: -7.5069
Max Act: 6.9132. Min Act: -0.1700
Data Index: 4613070 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5069. Min Range: -7.5069
Max Act: 6.9132. Min Act: -0.1700
Data Index: 2324492 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5069. Min Range: -7.5069
Max Act: 6.9132. Min Act: -0.1700
Data Index: 3420516 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5069. Min Range: -7.5069
Max Act: 6.8507. Min Act: -0.1700
Data Index: 1841856 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5069. Min Range: -7.5069
Max Act: 6.8507. Min Act: -0.1700
Data Index: 4089221 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19