Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2092 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.5084. Min Act: -0.1700
Data Index: 1454001 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.4459. Min Act: -0.1700
Data Index: 1389659 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.3521. Min Act: -0.1700
Data Index: 473601 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.3521. Min Act: -0.1700
Data Index: 1501324 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.3209. Min Act: -0.1700
Data Index: 4653230 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.3209. Min Act: -0.1700
Data Index: 8112954 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.2271. Min Act: -0.1700
Data Index: 1071277 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.2271. Min Act: -0.1700
Data Index: 5703254 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.1958. Min Act: -0.1700
Data Index: 1410496 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.1958. Min Act: -0.1700
Data Index: 8267880 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.1958. Min Act: -0.1700
Data Index: 1917456 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.1958. Min Act: -0.1700
Data Index: 3108662 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.1958. Min Act: -0.1700
Data Index: 6689596 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.1646. Min Act: -0.1700
Data Index: 1131106 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.1646. Min Act: -0.1700
Data Index: 3201369 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.1646. Min Act: -0.1700
Data Index: 8350659 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.1646. Min Act: -0.1700
Data Index: 2343569 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.1333. Min Act: -0.1700
Data Index: 8260476 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.1646. Min Act: -0.1700
Data Index: 5476125 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5084. Min Range: -4.5084
Max Act: 4.1333. Min Act: -0.1700
Data Index: 3203867 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19