Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 914 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.8865. Min Act: -0.1700
Data Index: 8476630 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.8865. Min Act: -0.1700
Data Index: 1112539 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.8552. Min Act: -0.1700
Data Index: 134247 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.8240. Min Act: -0.1700
Data Index: 2994245 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.8240. Min Act: -0.1700
Data Index: 736603 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.8240. Min Act: -0.1700
Data Index: 4905240 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.8240. Min Act: -0.1700
Data Index: 3100866 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7927. Min Act: -0.1700
Data Index: 3352094 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7927. Min Act: -0.1700
Data Index: 3759307 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7927. Min Act: -0.1700
Data Index: 4787946 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7927. Min Act: -0.1700
Data Index: 8165108 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7927. Min Act: -0.1700
Data Index: 7847527 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7615. Min Act: -0.1699
Data Index: 3897408 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7615. Min Act: -0.1700
Data Index: 3315529 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7302. Min Act: -0.1700
Data Index: 5991724 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7302. Min Act: -0.1700
Data Index: 6308437 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7302. Min Act: -0.1700
Data Index: 7659204 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7302. Min Act: -0.1700
Data Index: 4149059 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7302. Min Act: -0.1700
Data Index: 79926 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8865. Min Range: -5.8865
Max Act: 5.7302. Min Act: -0.1700
Data Index: 4456539 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19