Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0054. Min Range: -7.0054
Max Act: 7.0054. Min Act: -0.1700
Data Index: 2816555 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.6304. Min Act: -0.1700
Data Index: 2393439 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.6304. Min Act: -0.1700
Data Index: 7702067 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.5679. Min Act: -0.1700
Data Index: 6379621 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.5366. Min Act: -0.1700
Data Index: 7083367 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.5054. Min Act: -0.1700
Data Index: 2446413 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.5054. Min Act: -0.1700
Data Index: 5754358 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.4741. Min Act: -0.1700
Data Index: 911216 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.4429. Min Act: -0.1700
Data Index: 8443187 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.4116. Min Act: -0.1700
Data Index: 4459479 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.3804. Min Act: -0.1700
Data Index: 6135116 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.3179. Min Act: -0.1700
Data Index: 1106715 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.3179. Min Act: -0.1700
Data Index: 7512707 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.3179. Min Act: -0.1700
Data Index: 4620438 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.3179. Min Act: -0.1700
Data Index: 3839214 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.2866. Min Act: -0.1700
Data Index: 5879318 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.2866. Min Act: -0.1700
Data Index: 8004011 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.2554. Min Act: -0.1700
Data Index: 7809151 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.2554. Min Act: -0.1700
Data Index: 6487122 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0054. Min Range: -7.0054
Max Act: 6.2554. Min Act: -0.1700
Data Index: 6548665 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19