Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0476. Min Range: -8.0476
Max Act: 8.0476. Min Act: -0.1699
Data Index: 1623564 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.9851. Min Act: -0.1700
Data Index: 423871 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.9226. Min Act: -0.1700
Data Index: 2468248 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.9226. Min Act: -0.1700
Data Index: 5639706 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.8601. Min Act: -0.1700
Data Index: 3629268 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.8601. Min Act: -0.1700
Data Index: 3688925 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.7976. Min Act: -0.1700
Data Index: 4799900 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.7976. Min Act: -0.1700
Data Index: 1618570 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.7976. Min Act: -0.1700
Data Index: 4277906 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.7976. Min Act: -0.1700
Data Index: 3688929 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.7976. Min Act: -0.1700
Data Index: 4110475 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.7351. Min Act: -0.1700
Data Index: 5559681 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.7351. Min Act: -0.1699
Data Index: 4578200 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.7351. Min Act: -0.1699
Data Index: 8026638 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.6726. Min Act: -0.1700
Data Index: 2663775 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.6726. Min Act: -0.1700
Data Index: 5363966 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.6726. Min Act: -0.1700
Data Index: 6023583 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.6726. Min Act: -0.1700
Data Index: 4869976 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.6726. Min Act: -0.1700
Data Index: 7916173 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0476. Min Range: -8.0476
Max Act: 7.6726. Min Act: -0.1700
Data Index: 5342415 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19