Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 800 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.9032. Min Act: -0.1700
Data Index: 1756965 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.7782. Min Act: -0.1700
Data Index: 3320407 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.7470. Min Act: -0.1700
Data Index: 1897390 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.7157. Min Act: -0.1700
Data Index: 7855832 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.7157. Min Act: -0.1700
Data Index: 1650262 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.6220. Min Act: -0.1700
Data Index: 3183975 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.6532. Min Act: -0.1700
Data Index: 3844676 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.6220. Min Act: -0.1700
Data Index: 202953 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.5907. Min Act: -0.1700
Data Index: 1517730 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.5595. Min Act: -0.1700
Data Index: 6819675 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.5595. Min Act: -0.1700
Data Index: 662111 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.5595. Min Act: -0.1700
Data Index: 5090927 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.5282. Min Act: -0.1700
Data Index: 4587676 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.5282. Min Act: -0.1700
Data Index: 4128823 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.5595. Min Act: -0.1700
Data Index: 89634 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.5282. Min Act: -0.1700
Data Index: 2611576 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.5282. Min Act: -0.1700
Data Index: 3769340 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.5282. Min Act: -0.1700
Data Index: 7388800 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.4657. Min Act: -0.1700
Data Index: 8096676 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9032. Min Range: -6.9032
Max Act: 6.4657. Min Act: -0.1700
Data Index: 6650557 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19