Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1206 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4225. Min Range: -7.4225
Max Act: 7.4225. Min Act: -0.1700
Data Index: 1677505 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4225. Min Range: -7.4225
Max Act: 7.3288. Min Act: -0.1700
Data Index: 1184864 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4225. Min Range: -7.4225
Max Act: 7.2350. Min Act: -0.1700
Data Index: 8756457 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4225. Min Range: -7.4225
Max Act: 7.1413. Min Act: -0.1700
Data Index: 4659846 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4225. Min Range: -7.4225
Max Act: 7.1100. Min Act: -0.1700
Data Index: 8550183 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4225. Min Range: -7.4225
Max Act: 7.1100. Min Act: -0.1700
Data Index: 7275945 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4225. Min Range: -7.4225
Max Act: 7.0788. Min Act: -0.1700
Data Index: 3428870 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4225. Min Range: -7.4225
Max Act: 7.0788. Min Act: -0.1700
Data Index: 7447633 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4225. Min Range: -7.4225
Max Act: 7.0788. Min Act: -0.1700
Data Index: 4868937 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4225. Min Range: -7.4225
Max Act: 7.0475. Min Act: -0.1700
Data Index: 235654 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4225. Min Range: -7.4225
Max Act: 7.0163. Min Act: -0.1700
Data Index: 7245010 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4225. Min Range: -7.4225
Max Act: 6.9850. Min Act: -0.1700
Data Index: 3658002 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4225. Min Range: -7.4225
Max Act: 7.0163. Min Act: -0.1700
Data Index: 2143072 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4225. Min Range: -7.4225
Max Act: 6.9538. Min Act: -0.1700
Data Index: 75140 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4225. Min Range: -7.4225
Max Act: 6.9538. Min Act: -0.1700
Data Index: 6540612 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4225. Min Range: -7.4225
Max Act: 6.9538. Min Act: -0.1700
Data Index: 7819387 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4225. Min Range: -7.4225
Max Act: 6.9538. Min Act: -0.1700
Data Index: 348813 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4225. Min Range: -7.4225
Max Act: 6.9225. Min Act: -0.1700
Data Index: 3080120 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4225. Min Range: -7.4225
Max Act: 6.9538. Min Act: -0.1700
Data Index: 7255774 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4225. Min Range: -7.4225
Max Act: 6.9538. Min Act: -0.1700
Data Index: 3167462 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19