Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2482. Min Range: -5.2482
Max Act: 5.2482. Min Act: -0.1700
Data Index: 4359461 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2482. Min Range: -5.2482
Max Act: 5.1232. Min Act: -0.1700
Data Index: 3354668 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2482. Min Range: -5.2482
Max Act: 5.1232. Min Act: -0.1700
Data Index: 5072081 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2482. Min Range: -5.2482
Max Act: 5.0920. Min Act: -0.1700
Data Index: 273991 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2482. Min Range: -5.2482
Max Act: 5.0607. Min Act: -0.1700
Data Index: 8397841 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2482. Min Range: -5.2482
Max Act: 5.0295. Min Act: -0.1700
Data Index: 4276530 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.9670. Min Act: -0.1700
Data Index: 4957509 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.9670. Min Act: -0.1700
Data Index: 6417521 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.9357. Min Act: -0.1700
Data Index: 7739571 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.9357. Min Act: -0.1700
Data Index: 4801415 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.9045. Min Act: -0.1700
Data Index: 3546905 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.8732. Min Act: -0.1700
Data Index: 2115243 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.8420. Min Act: -0.1700
Data Index: 7247502 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.9045. Min Act: -0.1700
Data Index: 8745565 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.8732. Min Act: -0.1700
Data Index: 8825294 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.9357. Min Act: -0.1700
Data Index: 6070705 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.8420. Min Act: -0.1700
Data Index: 3455494 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.8732. Min Act: -0.1700
Data Index: 2697377 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.9045. Min Act: -0.1700
Data Index: 4175910 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2482. Min Range: -5.2482
Max Act: 4.8732. Min Act: -0.1700
Data Index: 117122 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19