Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3195. Min Range: -6.3195
Max Act: 6.3195. Min Act: -0.1700
Data Index: 1211310 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3195. Min Range: -6.3195
Max Act: 6.2258. Min Act: -0.1700
Data Index: 3819715 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3195. Min Range: -6.3195
Max Act: 6.1320. Min Act: -0.1700
Data Index: 1264123 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3195. Min Range: -6.3195
Max Act: 6.0383. Min Act: -0.1700
Data Index: 8036995 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.9758. Min Act: -0.1700
Data Index: 772227 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.9445. Min Act: -0.1700
Data Index: 7671602 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.8820. Min Act: -0.1700
Data Index: 3259997 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.8508. Min Act: -0.1700
Data Index: 8638825 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.8508. Min Act: -0.1700
Data Index: 6467430 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.8508. Min Act: -0.1700
Data Index: 3552166 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.8508. Min Act: -0.1700
Data Index: 7984448 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.8508. Min Act: -0.1700
Data Index: 2761663 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.7883. Min Act: -0.1700
Data Index: 833531 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.7570. Min Act: -0.1700
Data Index: 6702806 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.7570. Min Act: -0.1700
Data Index: 5107781 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.7883. Min Act: -0.1700
Data Index: 992703 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.7883. Min Act: -0.1700
Data Index: 2433101 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.7883. Min Act: -0.1700
Data Index: 6200941 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.7570. Min Act: -0.1700
Data Index: 7535304 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3195. Min Range: -6.3195
Max Act: 5.7258. Min Act: -0.1700
Data Index: 1029464 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19