Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2635 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.9297. Min Act: -0.1700
Data Index: 1403227 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7109. Min Act: -0.1700
Data Index: 309457 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.6797. Min Act: -0.1700
Data Index: 2260397 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.6484. Min Act: -0.1700
Data Index: 5970840 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.5859. Min Act: -0.1700
Data Index: 3472322 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.5547. Min Act: -0.1700
Data Index: 433280 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.5547. Min Act: -0.1700
Data Index: 7040187 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.5547. Min Act: -0.1700
Data Index: 2306578 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.5547. Min Act: -0.1700
Data Index: 70868 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.5547. Min Act: -0.1700
Data Index: 8195386 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.5234. Min Act: -0.1700
Data Index: 8131625 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.4922. Min Act: -0.1700
Data Index: 8156071 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.5234. Min Act: -0.1700
Data Index: 7471916 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.4922. Min Act: -0.1700
Data Index: 1489209 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.4609. Min Act: -0.1700
Data Index: 8486240 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.4609. Min Act: -0.1700
Data Index: 8828100 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.4609. Min Act: -0.1700
Data Index: 2362744 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.4297. Min Act: -0.1700
Data Index: 4745905 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.4297. Min Act: -0.1700
Data Index: 2013342 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.3984. Min Act: -0.1700
Data Index: 3449950 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19