Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5282 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8666. Min Range: -8.8666
Max Act: 8.8666. Min Act: -0.1700
Data Index: 3874964 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8666. Min Range: -8.8666
Max Act: 8.6166. Min Act: -0.1700
Data Index: 7853057 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8666. Min Range: -8.8666
Max Act: 8.5541. Min Act: -0.1700
Data Index: 5012607 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8666. Min Range: -8.8666
Max Act: 8.4291. Min Act: -0.1700
Data Index: 8453434 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8666. Min Range: -8.8666
Max Act: 8.3041. Min Act: -0.1700
Data Index: 5014178 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8666. Min Range: -8.8666
Max Act: 8.3041. Min Act: -0.1700
Data Index: 5199729 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8666. Min Range: -8.8666
Max Act: 8.2416. Min Act: -0.1700
Data Index: 5812514 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8666. Min Range: -8.8666
Max Act: 8.1791. Min Act: -0.1700
Data Index: 2755499 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8666. Min Range: -8.8666
Max Act: 8.1791. Min Act: -0.1700
Data Index: 6649311 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8666. Min Range: -8.8666
Max Act: 8.1166. Min Act: -0.1700
Data Index: 3243199 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8666. Min Range: -8.8666
Max Act: 8.1166. Min Act: -0.1700
Data Index: 3643431 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8666. Min Range: -8.8666
Max Act: 8.0541. Min Act: -0.1700
Data Index: 7456518 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8666. Min Range: -8.8666
Max Act: 7.9291. Min Act: -0.1700
Data Index: 7364314 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8666. Min Range: -8.8666
Max Act: 7.9291. Min Act: -0.1700
Data Index: 6717754 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8666. Min Range: -8.8666
Max Act: 7.9291. Min Act: -0.1700
Data Index: 1016697 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8666. Min Range: -8.8666
Max Act: 7.8666. Min Act: -0.1700
Data Index: 1616499 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8666. Min Range: -8.8666
Max Act: 7.8666. Min Act: -0.1700
Data Index: 13709 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8666. Min Range: -8.8666
Max Act: 7.8666. Min Act: -0.1700
Data Index: 4722725 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8666. Min Range: -8.8666
Max Act: 7.8041. Min Act: -0.1700
Data Index: 68152 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8666. Min Range: -8.8666
Max Act: 7.7416. Min Act: -0.1700
Data Index: 6698796 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19