Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3355 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.8961. Min Act: -0.1700
Data Index: 8256527 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.9273. Min Act: -0.1700
Data Index: 7410608 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.8961. Min Act: -0.1700
Data Index: 5515873 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.8336. Min Act: -0.1700
Data Index: 2463517 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.7086. Min Act: -0.1700
Data Index: 5537381 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.5836. Min Act: -0.1700
Data Index: 3501358 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.6148. Min Act: -0.1700
Data Index: 7491077 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.6461. Min Act: -0.1700
Data Index: 5995443 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.6148. Min Act: -0.1700
Data Index: 5145208 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.5523. Min Act: -0.1700
Data Index: 876380 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.5211. Min Act: -0.1700
Data Index: 3434058 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.5211. Min Act: -0.1700
Data Index: 4737660 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.4898. Min Act: -0.1700
Data Index: 3945877 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.4586. Min Act: -0.1700
Data Index: 4907308 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.4586. Min Act: -0.1700
Data Index: 2048246 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.3961. Min Act: -0.1700
Data Index: 6784216 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.3961. Min Act: -0.1700
Data Index: 5372786 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.3336. Min Act: -0.1700
Data Index: 6657810 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.3648. Min Act: -0.1700
Data Index: 2607430 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9273. Min Range: -6.9273
Max Act: 6.3648. Min Act: -0.1700
Data Index: 3517140 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19