Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.5862. Min Act: -0.1700
Data Index: 4900134 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.5237. Min Act: -0.1700
Data Index: 5037089 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.5237. Min Act: -0.1700
Data Index: 752868 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.5237. Min Act: -0.1700
Data Index: 1085443 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4925. Min Act: -0.1700
Data Index: 4145004 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.5237. Min Act: -0.1700
Data Index: 4505315 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4925. Min Act: -0.1700
Data Index: 4750076 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4925. Min Act: -0.1700
Data Index: 7917895 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4925. Min Act: -0.1700
Data Index: 1480249 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4612. Min Act: -0.1700
Data Index: 4832835 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4612. Min Act: -0.1700
Data Index: 8749377 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4612. Min Act: -0.1700
Data Index: 3695150 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4925. Min Act: -0.1700
Data Index: 3092757 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4612. Min Act: -0.1700
Data Index: 7352586 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4300. Min Act: -0.1700
Data Index: 4754608 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4612. Min Act: -0.1700
Data Index: 274554 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4612. Min Act: -0.1700
Data Index: 6894750 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4612. Min Act: -0.1700
Data Index: 3846439 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4300. Min Act: -0.1700
Data Index: 6202897 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5862. Min Range: -4.5862
Max Act: 4.4300. Min Act: -0.1700
Data Index: 4989344 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19