Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1424 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.1488. Min Act: -0.1700
Data Index: 3926134 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0987. Min Act: -0.1700
Data Index: 6985366 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0987. Min Act: -0.1700
Data Index: 5593477 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0652. Min Act: -0.1700
Data Index: 3961746 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0652. Min Act: -0.1700
Data Index: 359187 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0820. Min Act: -0.1700
Data Index: 2416217 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0315. Min Act: -0.1700
Data Index: 275649 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0484. Min Act: -0.1700
Data Index: 825831 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0484. Min Act: -0.1700
Data Index: 2664240 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0147. Min Act: -0.1700
Data Index: 2514604 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0315. Min Act: -0.1700
Data Index: 2400315 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0147. Min Act: -0.1700
Data Index: 5367096 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0147. Min Act: -0.1700
Data Index: 499537 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1488. Min Range: -2.1488
Max Act: 1.9978. Min Act: -0.1700
Data Index: 5018529 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1488. Min Range: -2.1488
Max Act: 1.9978. Min Act: -0.1700
Data Index: 2416218 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1488. Min Range: -2.1488
Max Act: 1.9978. Min Act: -0.1700
Data Index: 4467766 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1488. Min Range: -2.1488
Max Act: 1.9978. Min Act: -0.1700
Data Index: 508339 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1488. Min Range: -2.1488
Max Act: 2.0147. Min Act: -0.1700
Data Index: 2530734 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1488. Min Range: -2.1488
Max Act: 1.9808. Min Act: -0.1700
Data Index: 1476041 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1488. Min Range: -2.1488
Max Act: 1.9808. Min Act: -0.1700
Data Index: 265967 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19