Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4973 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0674. Min Range: -7.0674
Max Act: 7.0674. Min Act: -0.1700
Data Index: 515654 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.9736. Min Act: -0.1700
Data Index: 6566513 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.9111. Min Act: -0.1700
Data Index: 3180448 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.8799. Min Act: -0.1700
Data Index: 7052806 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.8486. Min Act: -0.1700
Data Index: 2511516 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.8174. Min Act: -0.1700
Data Index: 111707 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.7861. Min Act: -0.1700
Data Index: 4654581 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.8174. Min Act: -0.1700
Data Index: 2612222 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.7861. Min Act: -0.1700
Data Index: 4771034 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.7861. Min Act: -0.1700
Data Index: 6691184 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.7236. Min Act: -0.1700
Data Index: 5891939 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.7549. Min Act: -0.1700
Data Index: 7461700 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.7549. Min Act: -0.1700
Data Index: 4801026 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.6924. Min Act: -0.1700
Data Index: 5953045 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.7236. Min Act: -0.1700
Data Index: 1616390 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.6924. Min Act: -0.1700
Data Index: 2389671 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.6611. Min Act: -0.1700
Data Index: 3128851 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.6611. Min Act: -0.1700
Data Index: 551538 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.6611. Min Act: -0.1700
Data Index: 3580646 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0674. Min Range: -7.0674
Max Act: 6.6299. Min Act: -0.1700
Data Index: 4798837 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19