Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2585 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.5067. Min Act: -0.1700
Data Index: 5142610 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.3817. Min Act: -0.1700
Data Index: 8286212 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.2879. Min Act: -0.1700
Data Index: 6243214 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.2254. Min Act: -0.1700
Data Index: 3584716 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.2567. Min Act: -0.1700
Data Index: 7315510 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.1942. Min Act: -0.1700
Data Index: 1008943 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.2254. Min Act: -0.1700
Data Index: 3954757 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.1629. Min Act: -0.1700
Data Index: 4529208 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.1942. Min Act: -0.1700
Data Index: 7291357 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.1629. Min Act: -0.1700
Data Index: 4568601 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.1004. Min Act: -0.1700
Data Index: 3485963 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.1004. Min Act: -0.1700
Data Index: 509601 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5067. Min Range: -7.5067
Max Act: 6.9754. Min Act: -0.1700
Data Index: 8336035 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.0067. Min Act: -0.1700
Data Index: 4079098 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5067. Min Range: -7.5067
Max Act: 7.0067. Min Act: -0.1700
Data Index: 3986806 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5067. Min Range: -7.5067
Max Act: 6.9442. Min Act: -0.1700
Data Index: 3336314 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5067. Min Range: -7.5067
Max Act: 6.9754. Min Act: -0.1700
Data Index: 4939704 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5067. Min Range: -7.5067
Max Act: 6.9754. Min Act: -0.1700
Data Index: 343171 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5067. Min Range: -7.5067
Max Act: 6.9129. Min Act: -0.1700
Data Index: 4788104 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5067. Min Range: -7.5067
Max Act: 6.9442. Min Act: -0.1700
Data Index: 6043802 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19