Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 503 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.7600. Min Act: -0.1700
Data Index: 1772008 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.6038. Min Act: -0.1700
Data Index: 1438061 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.5413. Min Act: -0.1700
Data Index: 2490463 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.5413. Min Act: -0.1700
Data Index: 6323490 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.5413. Min Act: -0.1700
Data Index: 3607567 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.5100. Min Act: -0.1700
Data Index: 7879236 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.4788. Min Act: -0.1700
Data Index: 1275274 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.4788. Min Act: -0.1700
Data Index: 1591141 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.5100. Min Act: -0.1700
Data Index: 5368255 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.4788. Min Act: -0.1700
Data Index: 7410601 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.5100. Min Act: -0.1700
Data Index: 5488563 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.4163. Min Act: -0.1700
Data Index: 6876500 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.4163. Min Act: -0.1700
Data Index: 5606516 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.4475. Min Act: -0.1700
Data Index: 4137245 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.4163. Min Act: -0.1700
Data Index: 4989345 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.3850. Min Act: -0.1700
Data Index: 3585734 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.3850. Min Act: -0.1700
Data Index: 1575621 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.3850. Min Act: -0.1700
Data Index: 2107882 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.3538. Min Act: -0.1700
Data Index: 5535760 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7600. Min Range: -4.7600
Max Act: 4.3850. Min Act: -0.1700
Data Index: 3737977 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19