Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4238 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4286. Min Range: -7.4286
Max Act: 7.4286. Min Act: -0.1700
Data Index: 2454156 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.9599. Min Act: -0.1700
Data Index: 1488227 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.9599. Min Act: -0.1700
Data Index: 1322648 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.7099. Min Act: -0.1700
Data Index: 1912568 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.7099. Min Act: -0.1700
Data Index: 5450859 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.7099. Min Act: -0.1700
Data Index: 1031505 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.7411. Min Act: -0.1700
Data Index: 8365462 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.7411. Min Act: -0.1700
Data Index: 5073621 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.7724. Min Act: -0.1700
Data Index: 5289517 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.7099. Min Act: -0.1700
Data Index: 7075345 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.6786. Min Act: -0.1700
Data Index: 8305916 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.6786. Min Act: -0.1700
Data Index: 202298 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.6786. Min Act: -0.1700
Data Index: 3756105 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.6474. Min Act: -0.1700
Data Index: 6045844 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.6474. Min Act: -0.1700
Data Index: 6712281 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.6161. Min Act: -0.1700
Data Index: 5935270 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.6161. Min Act: -0.1700
Data Index: 6609285 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.5849. Min Act: -0.1700
Data Index: 1716014 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.6161. Min Act: -0.1700
Data Index: 923332 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4286. Min Range: -7.4286
Max Act: 6.5849. Min Act: -0.1700
Data Index: 3775463 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19