Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 522 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.7139. Min Act: -0.1700
Data Index: 5760871 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.5264. Min Act: -0.1700
Data Index: 3799270 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.4951. Min Act: -0.1700
Data Index: 2801402 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.5264. Min Act: -0.1700
Data Index: 651013 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.4639. Min Act: -0.1700
Data Index: 6470089 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.5264. Min Act: -0.1700
Data Index: 3582857 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.4639. Min Act: -0.1700
Data Index: 3902978 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.4639. Min Act: -0.1700
Data Index: 8412463 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.4951. Min Act: -0.1700
Data Index: 2704019 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.4639. Min Act: -0.1700
Data Index: 3799272 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.4639. Min Act: -0.1700
Data Index: 6354289 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.4326. Min Act: -0.1700
Data Index: 8709738 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.4326. Min Act: -0.1700
Data Index: 7140553 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.4014. Min Act: -0.1700
Data Index: 5090962 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.4014. Min Act: -0.1700
Data Index: 6989029 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.3389. Min Act: -0.1700
Data Index: 3486170 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.4014. Min Act: -0.1700
Data Index: 147854 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.3389. Min Act: -0.1700
Data Index: 1185259 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.3389. Min Act: -0.1700
Data Index: 3799271 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7139. Min Range: -4.7139
Max Act: 4.3701. Min Act: -0.1700
Data Index: 5770904 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19