Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1742 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.7852. Min Act: -0.1700
Data Index: 7528111 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.7852. Min Act: -0.1700
Data Index: 2534710 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.6602. Min Act: -0.1700
Data Index: 4322986 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.6602. Min Act: -0.1700
Data Index: 1360985 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.5977. Min Act: -0.1700
Data Index: 2287439 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.5977. Min Act: -0.1700
Data Index: 2504125 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.5977. Min Act: -0.1700
Data Index: 4814630 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.4727. Min Act: -0.1700
Data Index: 710386 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.4727. Min Act: -0.1700
Data Index: 3932241 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.4727. Min Act: -0.1700
Data Index: 8745701 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.4102. Min Act: -0.1700
Data Index: 4941329 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.4102. Min Act: -0.1700
Data Index: 2695115 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.4102. Min Act: -0.1700
Data Index: 5709254 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.4102. Min Act: -0.1700
Data Index: 447194 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.3477. Min Act: -0.1700
Data Index: 6219515 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.3477. Min Act: -0.1700
Data Index: 5030282 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.3477. Min Act: -0.1700
Data Index: 4668947 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.3477. Min Act: -0.1700
Data Index: 6387621 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.2852. Min Act: -0.1700
Data Index: 3055474 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7852. Min Range: -8.7852
Max Act: 8.2852. Min Act: -0.1700
Data Index: 552277 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19