Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4336 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.8182. Min Act: -0.1700
Data Index: 1806464 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.6931. Min Act: -0.1700
Data Index: 7139165 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.6931. Min Act: -0.1700
Data Index: 6467457 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.6618. Min Act: -0.1700
Data Index: 4896747 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.6618. Min Act: -0.1700
Data Index: 807558 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.6618. Min Act: -0.1700
Data Index: 619216 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.6618. Min Act: -0.1700
Data Index: 2234730 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.6305. Min Act: -0.1698
Data Index: 779770 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.6305. Min Act: -0.1700
Data Index: 3640408 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.6305. Min Act: -0.1698
Data Index: 7087683 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.6305. Min Act: -0.1700
Data Index: 835123 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.5992. Min Act: -0.1700
Data Index: 7321595 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.5679. Min Act: -0.1700
Data Index: 5151635 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.5679. Min Act: -0.1700
Data Index: 5965309 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.5679. Min Act: -0.1700
Data Index: 3949600 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.5366. Min Act: -0.1700
Data Index: 4725644 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.5366. Min Act: -0.1700
Data Index: 2655182 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.5366. Min Act: -0.1700
Data Index: 6458618 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.5366. Min Act: -0.1700
Data Index: 2234723 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8182. Min Range: -3.8182
Max Act: 3.5366. Min Act: -0.1695
Data Index: 159838 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19