Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2775 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.8476. Min Act: -0.1700
Data Index: 7740471 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.7851. Min Act: -0.1700
Data Index: 1316458 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.6601. Min Act: -0.1700
Data Index: 982123 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.6288. Min Act: -0.1700
Data Index: 2911110 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.4726. Min Act: -0.1700
Data Index: 4094968 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.4726. Min Act: -0.1700
Data Index: 7158731 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.4413. Min Act: -0.1700
Data Index: 1469388 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.4101. Min Act: -0.1700
Data Index: 6173524 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.3788. Min Act: -0.1700
Data Index: 3859710 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.3163. Min Act: -0.1700
Data Index: 3890849 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.3476. Min Act: -0.1700
Data Index: 8770360 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.3476. Min Act: -0.1700
Data Index: 6111485 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.3163. Min Act: -0.1700
Data Index: 6226730 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.2851. Min Act: -0.1700
Data Index: 60688 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.2538. Min Act: -0.1700
Data Index: 2869752 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.2538. Min Act: -0.1700
Data Index: 1566530 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.2538. Min Act: -0.1700
Data Index: 670022 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.2226. Min Act: -0.1700
Data Index: 8187934 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.2538. Min Act: -0.1700
Data Index: 3347873 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8476. Min Range: -5.8476
Max Act: 5.2538. Min Act: -0.1700
Data Index: 1624249 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19