Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 859 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2567. Min Range: -5.2567
Max Act: 5.2567. Min Act: -0.1700
Data Index: 8817648 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2567. Min Range: -5.2567
Max Act: 5.2254. Min Act: -0.1700
Data Index: 1229734 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2567. Min Range: -5.2567
Max Act: 5.1004. Min Act: -0.1700
Data Index: 7876149 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2567. Min Range: -5.2567
Max Act: 5.1317. Min Act: -0.1700
Data Index: 6073291 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2567. Min Range: -5.2567
Max Act: 5.1317. Min Act: -0.1700
Data Index: 1818721 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2567. Min Range: -5.2567
Max Act: 5.1317. Min Act: -0.1700
Data Index: 4062677 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2567. Min Range: -5.2567
Max Act: 5.1004. Min Act: -0.1700
Data Index: 4826379 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2567. Min Range: -5.2567
Max Act: 5.0379. Min Act: -0.1700
Data Index: 4462780 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2567. Min Range: -5.2567
Max Act: 5.1004. Min Act: -0.1700
Data Index: 2594748 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2567. Min Range: -5.2567
Max Act: 5.1004. Min Act: -0.1700
Data Index: 5628805 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2567. Min Range: -5.2567
Max Act: 5.0067. Min Act: -0.1700
Data Index: 7296254 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.9754. Min Act: -0.1700
Data Index: 4542394 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.9754. Min Act: -0.1700
Data Index: 3714042 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.9442. Min Act: -0.1700
Data Index: 7118940 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.9442. Min Act: -0.1700
Data Index: 2788080 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.9754. Min Act: -0.1700
Data Index: 349702 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.9754. Min Act: -0.1700
Data Index: 8280149 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.9754. Min Act: -0.1700
Data Index: 5218354 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.9442. Min Act: -0.1700
Data Index: 2000884 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.9442. Min Act: -0.1700
Data Index: 2218565 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19