Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3543 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.8365. Min Act: -0.1700
Data Index: 296676 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7115. Min Act: -0.1700
Data Index: 2293230 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.6490. Min Act: -0.1700
Data Index: 5448150 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.6490. Min Act: -0.1700
Data Index: 5554794 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.6490. Min Act: -0.1700
Data Index: 6308318 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.6490. Min Act: -0.1700
Data Index: 8259838 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.6490. Min Act: -0.1700
Data Index: 8713458 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.5865. Min Act: -0.1700
Data Index: 5151652 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.5865. Min Act: -0.1700
Data Index: 4589778 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.5865. Min Act: -0.1700
Data Index: 5699017 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.5865. Min Act: -0.1700
Data Index: 161036 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.5240. Min Act: -0.1700
Data Index: 2767800 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.5240. Min Act: -0.1700
Data Index: 2246143 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.5240. Min Act: -0.1700
Data Index: 3098189 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.5240. Min Act: -0.1700
Data Index: 4589781 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.5240. Min Act: -0.1700
Data Index: 4589783 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.4302. Min Act: -0.1700
Data Index: 4887365 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.4615. Min Act: -0.1700
Data Index: 1236812 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.4615. Min Act: -0.1700
Data Index: 1791474 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.4615. Min Act: -0.1700
Data Index: 7383224 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19