Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4879 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.7674. Min Act: -0.1700
Data Index: 1404776 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.5799. Min Act: -0.1700
Data Index: 4957684 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.4861. Min Act: -0.1700
Data Index: 876709 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.3924. Min Act: -0.1700
Data Index: 2780389 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.4236. Min Act: -0.1700
Data Index: 5282233 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.4236. Min Act: -0.1700
Data Index: 3925188 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.3299. Min Act: -0.1700
Data Index: 2780382 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2986. Min Act: -0.1700
Data Index: 7771046 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2674. Min Act: -0.1700
Data Index: 4845928 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2361. Min Act: -0.1700
Data Index: 7264837 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2361. Min Act: -0.1700
Data Index: 3881701 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2361. Min Act: -0.1700
Data Index: 380828 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2361. Min Act: -0.1700
Data Index: 380829 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2361. Min Act: -0.1700
Data Index: 7963740 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2361. Min Act: -0.1700
Data Index: 4284562 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2049. Min Act: -0.1700
Data Index: 2418688 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2049. Min Act: -0.1700
Data Index: 2780391 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2049. Min Act: -0.1700
Data Index: 802063 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2049. Min Act: -0.1700
Data Index: 11071 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7674. Min Range: -5.7674
Max Act: 5.2049. Min Act: -0.1700
Data Index: 5187630 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19