Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5607 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4761. Min Range: -4.4761
Max Act: 4.4761. Min Act: -0.1700
Data Index: 1929724 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4761. Min Range: -4.4761
Max Act: 4.3198. Min Act: -0.1700
Data Index: 283304 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4761. Min Range: -4.4761
Max Act: 4.1636. Min Act: -0.1700
Data Index: 8332127 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4761. Min Range: -4.4761
Max Act: 4.0073. Min Act: -0.1700
Data Index: 641964 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.9760. Min Act: -0.1700
Data Index: 541574 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.9760. Min Act: -0.1700
Data Index: 5579022 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.9135. Min Act: -0.1700
Data Index: 1577153 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.9135. Min Act: -0.1700
Data Index: 1014228 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.8510. Min Act: -0.1700
Data Index: 879063 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.8822. Min Act: -0.1700
Data Index: 6797199 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.8822. Min Act: -0.1700
Data Index: 4330390 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.8822. Min Act: -0.1700
Data Index: 2412820 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.8822. Min Act: -0.1700
Data Index: 2664638 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.8822. Min Act: -0.1700
Data Index: 3740572 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.8510. Min Act: -0.1700
Data Index: 6249848 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.8510. Min Act: -0.1700
Data Index: 7718165 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.8510. Min Act: -0.1700
Data Index: 600624 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.8510. Min Act: -0.1700
Data Index: 7995855 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.8510. Min Act: -0.1700
Data Index: 4368763 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4761. Min Range: -4.4761
Max Act: 3.8510. Min Act: -0.1700
Data Index: 8013584 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19