Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 436 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.9808. Min Act: -0.1700
Data Index: 8366364 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.4808. Min Act: -0.1700
Data Index: 1042450 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.2308. Min Act: -0.1700
Data Index: 1455810 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.1996. Min Act: -0.1700
Data Index: 3973027 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.1683. Min Act: -0.1700
Data Index: 3273504 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.0746. Min Act: -0.1700
Data Index: 7016198 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.0746. Min Act: -0.1700
Data Index: 1455057 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.0433. Min Act: -0.1700
Data Index: 7134571 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.0433. Min Act: -0.1700
Data Index: 2788067 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.0121. Min Act: -0.1700
Data Index: 7918893 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.0121. Min Act: -0.1700
Data Index: 6799349 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.0121. Min Act: -0.1700
Data Index: 4370646 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9808. Min Range: -6.9808
Max Act: 6.0121. Min Act: -0.1700
Data Index: 775277 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9808. Min Range: -6.9808
Max Act: 5.9808. Min Act: -0.1700
Data Index: 7960809 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9808. Min Range: -6.9808
Max Act: 5.9808. Min Act: -0.1700
Data Index: 8607983 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9808. Min Range: -6.9808
Max Act: 5.9808. Min Act: -0.1700
Data Index: 7214269 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9808. Min Range: -6.9808
Max Act: 5.9496. Min Act: -0.1700
Data Index: 8415177 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9808. Min Range: -6.9808
Max Act: 5.9183. Min Act: -0.1700
Data Index: 6306155 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9808. Min Range: -6.9808
Max Act: 5.9183. Min Act: -0.1700
Data Index: 7010649 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9808. Min Range: -6.9808
Max Act: 5.9183. Min Act: -0.1700
Data Index: 1149402 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19