Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4542 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4451. Min Range: -6.4451
Max Act: 6.4451. Min Act: -0.1700
Data Index: 2986768 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4451. Min Range: -6.4451
Max Act: 6.4139. Min Act: -0.1700
Data Index: 3893417 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4451. Min Range: -6.4451
Max Act: 6.3201. Min Act: -0.1700
Data Index: 4894028 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4451. Min Range: -6.4451
Max Act: 6.3514. Min Act: -0.1700
Data Index: 4982273 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4451. Min Range: -6.4451
Max Act: 6.1639. Min Act: -0.1700
Data Index: 80920 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4451. Min Range: -6.4451
Max Act: 6.1326. Min Act: -0.1700
Data Index: 497647 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4451. Min Range: -6.4451
Max Act: 6.1326. Min Act: -0.1700
Data Index: 3406285 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4451. Min Range: -6.4451
Max Act: 6.1326. Min Act: -0.1700
Data Index: 1364578 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4451. Min Range: -6.4451
Max Act: 6.0076. Min Act: -0.1700
Data Index: 3194273 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4451. Min Range: -6.4451
Max Act: 5.9764. Min Act: -0.1700
Data Index: 5919425 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4451. Min Range: -6.4451
Max Act: 5.9764. Min Act: -0.1700
Data Index: 3114260 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4451. Min Range: -6.4451
Max Act: 5.9764. Min Act: -0.1700
Data Index: 4084959 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4451. Min Range: -6.4451
Max Act: 5.9451. Min Act: -0.1700
Data Index: 1997365 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4451. Min Range: -6.4451
Max Act: 5.9451. Min Act: -0.1700
Data Index: 5625603 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4451. Min Range: -6.4451
Max Act: 5.9139. Min Act: -0.1700
Data Index: 2749238 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4451. Min Range: -6.4451
Max Act: 5.9139. Min Act: -0.1700
Data Index: 2983192 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4451. Min Range: -6.4451
Max Act: 5.8826. Min Act: -0.1700
Data Index: 4119411 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4451. Min Range: -6.4451
Max Act: 5.8514. Min Act: -0.1700
Data Index: 3284858 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4451. Min Range: -6.4451
Max Act: 5.8201. Min Act: -0.1700
Data Index: 5579701 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4451. Min Range: -6.4451
Max Act: 5.8826. Min Act: -0.1700
Data Index: 1947681 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19