Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4448 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.4476. Min Act: -0.1700
Data Index: 5535015 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.3851. Min Act: -0.1700
Data Index: 4045522 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.3851. Min Act: -0.1700
Data Index: 2341500 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.3226. Min Act: -0.1700
Data Index: 631693 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.3226. Min Act: -0.1700
Data Index: 4580188 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.2601. Min Act: -0.1700
Data Index: 3819624 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.2601. Min Act: -0.1700
Data Index: 6156326 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.1976. Min Act: -0.1700
Data Index: 3414132 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.1976. Min Act: -0.1700
Data Index: 4690786 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.1976. Min Act: -0.1700
Data Index: 7882205 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.1351. Min Act: -0.1700
Data Index: 8254640 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.1351. Min Act: -0.1700
Data Index: 8389590 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.1351. Min Act: -0.1700
Data Index: 7520502 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.1351. Min Act: -0.1700
Data Index: 2857092 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.1351. Min Act: -0.1700
Data Index: 7272612 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.1351. Min Act: -0.1700
Data Index: 1784372 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.1351. Min Act: -0.1700
Data Index: 1410847 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.0726. Min Act: -0.1700
Data Index: 4858794 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.0726. Min Act: -0.1700
Data Index: 260607 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4476. Min Range: -7.4476
Max Act: 7.0726. Min Act: -0.1700
Data Index: 7100222 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19