Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3919 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0220. Min Range: -5.0220
Max Act: 5.0220. Min Act: -0.1700
Data Index: 2257542 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.9282. Min Act: -0.1700
Data Index: 3769071 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.8657. Min Act: -0.1700
Data Index: 373641 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.8970. Min Act: -0.1700
Data Index: 1698944 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.8032. Min Act: -0.1700
Data Index: 754150 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.7407. Min Act: -0.1700
Data Index: 7607543 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.7095. Min Act: -0.1700
Data Index: 2996980 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.6782. Min Act: -0.1700
Data Index: 7065239 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.6782. Min Act: -0.1700
Data Index: 2464515 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.6470. Min Act: -0.1700
Data Index: 5396679 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.6470. Min Act: -0.1700
Data Index: 5497813 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.6470. Min Act: -0.1700
Data Index: 7454382 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.6157. Min Act: -0.1700
Data Index: 3880421 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.6157. Min Act: -0.1700
Data Index: 1589701 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.6157. Min Act: -0.1700
Data Index: 2776544 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.5845. Min Act: -0.1700
Data Index: 8514460 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.5219. Min Act: -0.1700
Data Index: 7454379 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.5532. Min Act: -0.1700
Data Index: 4304782 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.5532. Min Act: -0.1700
Data Index: 7832340 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0220. Min Range: -5.0220
Max Act: 4.5532. Min Act: -0.1700
Data Index: 4546022 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19