Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1683 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.8610. Min Act: -0.1700
Data Index: 1367761 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.2360. Min Act: -0.1700
Data Index: 3391606 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.2047. Min Act: -0.1700
Data Index: 5333256 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.2047. Min Act: -0.1700
Data Index: 922395 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.1110. Min Act: -0.1700
Data Index: 2585808 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.1110. Min Act: -0.1700
Data Index: 8166797 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.1110. Min Act: -0.1700
Data Index: 4531090 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.0797. Min Act: -0.1700
Data Index: 5767478 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.0797. Min Act: -0.1700
Data Index: 7601226 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.0172. Min Act: -0.1700
Data Index: 5812171 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.0797. Min Act: -0.1700
Data Index: 2954131 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.0797. Min Act: -0.1700
Data Index: 2651694 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.0797. Min Act: -0.1700
Data Index: 553523 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.0485. Min Act: -0.1700
Data Index: 7493419 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.0485. Min Act: -0.1700
Data Index: 2519871 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8610. Min Range: -7.8610
Max Act: 7.0172. Min Act: -0.1700
Data Index: 7539547 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8610. Min Range: -7.8610
Max Act: 6.9860. Min Act: -0.1700
Data Index: 7471527 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8610. Min Range: -7.8610
Max Act: 6.9860. Min Act: -0.1700
Data Index: 5664660 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8610. Min Range: -7.8610
Max Act: 6.9860. Min Act: -0.1700
Data Index: 4470276 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8610. Min Range: -7.8610
Max Act: 6.9235. Min Act: -0.1700
Data Index: 2752591 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19