Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3937 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2229. Min Range: -5.2229
Max Act: 5.2229. Min Act: -0.1700
Data Index: 5292212 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2229. Min Range: -5.2229
Max Act: 5.0354. Min Act: -0.1700
Data Index: 6495487 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2229. Min Range: -5.2229
Max Act: 5.0041. Min Act: -0.1700
Data Index: 1151688 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9729. Min Act: -0.1700
Data Index: 873626 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9729. Min Act: -0.1700
Data Index: 8061731 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9729. Min Act: -0.1700
Data Index: 5575991 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9104. Min Act: -0.1700
Data Index: 3478821 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.8479. Min Act: -0.1700
Data Index: 2945793 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.8166. Min Act: -0.1700
Data Index: 7942762 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.8166. Min Act: -0.1700
Data Index: 8072420 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.7854. Min Act: -0.1700
Data Index: 1972597 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.7854. Min Act: -0.1700
Data Index: 7195410 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.8166. Min Act: -0.1700
Data Index: 4870554 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.7541. Min Act: -0.1700
Data Index: 4574550 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.7541. Min Act: -0.1700
Data Index: 1095575 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.7541. Min Act: -0.1700
Data Index: 8820563 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.6916. Min Act: -0.1700
Data Index: 2470520 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.6916. Min Act: -0.1700
Data Index: 2716776 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.6916. Min Act: -0.1700
Data Index: 185515 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.6916. Min Act: -0.1700
Data Index: 7868610 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19