Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 67 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.6604. Min Act: -0.1700
Data Index: 6278373 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5352. Min Act: -0.1700
Data Index: 4519568 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5352. Min Act: -0.1700
Data Index: 827254 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5039. Min Act: -0.1700
Data Index: 2620450 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5039. Min Act: -0.1700
Data Index: 2066676 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5039. Min Act: -0.1700
Data Index: 7919512 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4725. Min Act: -0.1700
Data Index: 614008 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4725. Min Act: -0.1700
Data Index: 8305910 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4725. Min Act: -0.1700
Data Index: 4606656 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4725. Min Act: -0.1700
Data Index: 490583 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4725. Min Act: -0.1700
Data Index: 4545216 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4725. Min Act: -0.1700
Data Index: 7428592 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4725. Min Act: -0.1700
Data Index: 3880121 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4725. Min Act: -0.1700
Data Index: 6949319 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4412. Min Act: -0.1700
Data Index: 1443032 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4412. Min Act: -0.1700
Data Index: 827250 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4412. Min Act: -0.1700
Data Index: 2704220 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4412. Min Act: -0.1700
Data Index: 4745768 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4412. Min Act: -0.1700
Data Index: 5841078 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.4412. Min Act: -0.1700
Data Index: 6383529 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19