Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2111 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.5404. Min Act: -0.1700
Data Index: 552257 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.5091. Min Act: -0.1700
Data Index: 5580752 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4934. Min Act: -0.1700
Data Index: 2160191 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4778. Min Act: -0.1700
Data Index: 4961600 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4464. Min Act: -0.1700
Data Index: 6092355 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4464. Min Act: -0.1700
Data Index: 1016797 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4464. Min Act: -0.1700
Data Index: 1140271 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4464. Min Act: -0.1700
Data Index: 2782453 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4151. Min Act: -0.1700
Data Index: 5962801 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4308. Min Act: -0.1700
Data Index: 1540616 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4308. Min Act: -0.1700
Data Index: 2769934 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4464. Min Act: -0.1700
Data Index: 4554378 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4464. Min Act: -0.1700
Data Index: 4661508 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4151. Min Act: -0.1700
Data Index: 1484485 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.3994. Min Act: -0.1700
Data Index: 736610 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4151. Min Act: -0.1700
Data Index: 4026156 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4308. Min Act: -0.1700
Data Index: 105971 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4151. Min Act: -0.1700
Data Index: 2916644 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4308. Min Act: -0.1700
Data Index: 2328527 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5404. Min Range: -3.5404
Max Act: 3.4151. Min Act: -0.1700
Data Index: 3995690 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19