Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4062 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9694. Min Act: -0.1700
Data Index: 1359002 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9694. Min Act: -0.1700
Data Index: 7209105 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9694. Min Act: -0.1700
Data Index: 7064448 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9382. Min Act: -0.1700
Data Index: 2580985 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9382. Min Act: -0.1700
Data Index: 6709158 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9382. Min Act: -0.1700
Data Index: 8268101 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9069. Min Act: -0.1700
Data Index: 2700654 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9382. Min Act: -0.1700
Data Index: 1979914 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9069. Min Act: -0.1700
Data Index: 5766629 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.8757. Min Act: -0.1700
Data Index: 1634186 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9069. Min Act: -0.1700
Data Index: 1187494 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.8444. Min Act: -0.1700
Data Index: 3642903 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.8757. Min Act: -0.1700
Data Index: 1104397 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9069. Min Act: -0.1700
Data Index: 7182403 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9382. Min Act: -0.1700
Data Index: 6606168 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9069. Min Act: -0.1700
Data Index: 1583429 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.9069. Min Act: -0.1700
Data Index: 2573634 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.8757. Min Act: -0.1700
Data Index: 2720339 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.8757. Min Act: -0.1700
Data Index: 4111785 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9694. Min Range: -6.9694
Max Act: 6.8757. Min Act: -0.1700
Data Index: 2169926 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19