Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.4287. Min Act: -0.1700
Data Index: 7706999 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.4287. Min Act: -0.1700
Data Index: 5291593 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.3662. Min Act: -0.1700
Data Index: 4118651 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.3350. Min Act: -0.1700
Data Index: 6301615 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.2725. Min Act: -0.1700
Data Index: 2111349 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.2412. Min Act: -0.1700
Data Index: 8450801 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.2412. Min Act: -0.1700
Data Index: 6983495 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.2100. Min Act: -0.1700
Data Index: 190147 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.2100. Min Act: -0.1700
Data Index: 1685022 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.1475. Min Act: -0.1700
Data Index: 2943434 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.1475. Min Act: -0.1700
Data Index: 664683 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.1162. Min Act: -0.1700
Data Index: 1383610 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.1162. Min Act: -0.1700
Data Index: 7197744 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.0850. Min Act: -0.1700
Data Index: 6775811 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.0850. Min Act: -0.1700
Data Index: 267555 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.0850. Min Act: -0.1700
Data Index: 7460769 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.0537. Min Act: -0.1700
Data Index: 1438655 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.0537. Min Act: -0.1700
Data Index: 4144818 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.0537. Min Act: -0.1700
Data Index: 3734179 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4287. Min Range: -6.4287
Max Act: 6.0225. Min Act: -0.1700
Data Index: 2825256 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19