Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2198 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.4174. Min Act: -0.1700
Data Index: 7591931 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.3237. Min Act: -0.1700
Data Index: 1161416 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.2612. Min Act: -0.1700
Data Index: 53168 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.2299. Min Act: -0.1700
Data Index: 7072888 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.1987. Min Act: -0.1700
Data Index: 5447684 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.1674. Min Act: -0.1700
Data Index: 125150 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.1674. Min Act: -0.1700
Data Index: 1742274 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.1362. Min Act: -0.1700
Data Index: 7652675 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.1674. Min Act: -0.1700
Data Index: 4431786 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.1049. Min Act: -0.1700
Data Index: 827886 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.1362. Min Act: -0.1700
Data Index: 529731 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.1049. Min Act: -0.1700
Data Index: 5130867 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.0737. Min Act: -0.1700
Data Index: 5206637 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.0737. Min Act: -0.1700
Data Index: 1507330 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.0424. Min Act: -0.1700
Data Index: 6096252 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4174. Min Range: -6.4174
Max Act: 6.0112. Min Act: -0.1700
Data Index: 882444 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4174. Min Range: -6.4174
Max Act: 5.9799. Min Act: -0.1700
Data Index: 3675942 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4174. Min Range: -6.4174
Max Act: 5.9799. Min Act: -0.1700
Data Index: 2449108 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4174. Min Range: -6.4174
Max Act: 5.9487. Min Act: -0.1700
Data Index: 4698514 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4174. Min Range: -6.4174
Max Act: 5.9487. Min Act: -0.1700
Data Index: 760129 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19