Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3969 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0153. Min Range: -5.0153
Max Act: 5.0153. Min Act: -0.1700
Data Index: 8017459 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.5778. Min Act: -0.1700
Data Index: 3654912 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.5778. Min Act: -0.1700
Data Index: 839769 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.5153. Min Act: -0.1700
Data Index: 3187538 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.5153. Min Act: -0.1700
Data Index: 2697392 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.4841. Min Act: -0.1700
Data Index: 3568051 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.4841. Min Act: -0.1700
Data Index: 2730882 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.4528. Min Act: -0.1700
Data Index: 3761795 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.4528. Min Act: -0.1700
Data Index: 4956677 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.4528. Min Act: -0.1700
Data Index: 1648232 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.4528. Min Act: -0.1700
Data Index: 6449043 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.4216. Min Act: -0.1700
Data Index: 2106627 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.3903. Min Act: -0.1700
Data Index: 6840556 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.4216. Min Act: -0.1700
Data Index: 5501103 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.4216. Min Act: -0.1700
Data Index: 1482617 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.3903. Min Act: -0.1700
Data Index: 711794 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.3903. Min Act: -0.1700
Data Index: 5342704 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.3903. Min Act: -0.1700
Data Index: 6765786 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.3591. Min Act: -0.1700
Data Index: 4170719 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0153. Min Range: -5.0153
Max Act: 4.3903. Min Act: -0.1700
Data Index: 3172616 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19