Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3160 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.8425. Min Act: -0.1700
Data Index: 2390518 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.5612. Min Act: -0.1700
Data Index: 2449484 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.4675. Min Act: -0.1700
Data Index: 6128520 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.4362. Min Act: -0.1700
Data Index: 403539 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.3737. Min Act: -0.1700
Data Index: 5512752 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.3112. Min Act: -0.1700
Data Index: 8354021 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.3112. Min Act: -0.1700
Data Index: 6123918 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.2800. Min Act: -0.1700
Data Index: 8317680 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.2800. Min Act: -0.1700
Data Index: 91689 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.2487. Min Act: -0.1700
Data Index: 7126932 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.2487. Min Act: -0.1700
Data Index: 4221279 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.2487. Min Act: -0.1700
Data Index: 1310927 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.2175. Min Act: -0.1700
Data Index: 6072432 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.2175. Min Act: -0.1700
Data Index: 6432824 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.2175. Min Act: -0.1700
Data Index: 1185195 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.1862. Min Act: -0.1700
Data Index: 3090556 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.2175. Min Act: -0.1700
Data Index: 917988 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.1550. Min Act: -0.1700
Data Index: 6456054 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.1550. Min Act: -0.1700
Data Index: 3859731 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8425. Min Range: -5.8425
Max Act: 5.1237. Min Act: -0.1700
Data Index: 6997171 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19