Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.5396. Min Act: -0.1700
Data Index: 8538097 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.4146. Min Act: -0.1700
Data Index: 8432774 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.2896. Min Act: -0.1700
Data Index: 4187977 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.2584. Min Act: -0.1700
Data Index: 5014464 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.2584. Min Act: -0.1700
Data Index: 8258358 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.2271. Min Act: -0.1700
Data Index: 2275810 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.2271. Min Act: -0.1700
Data Index: 931947 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.2271. Min Act: -0.1700
Data Index: 3623903 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.1959. Min Act: -0.1700
Data Index: 5676869 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.2271. Min Act: -0.1700
Data Index: 995451 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.1959. Min Act: -0.1700
Data Index: 6353890 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.1959. Min Act: -0.1700
Data Index: 8151257 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.1959. Min Act: -0.1700
Data Index: 1913210 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.1646. Min Act: -0.1700
Data Index: 2991903 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.1646. Min Act: -0.1700
Data Index: 5638065 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.1646. Min Act: -0.1700
Data Index: 282335 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.1646. Min Act: -0.1700
Data Index: 8085881 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.1646. Min Act: -0.1700
Data Index: 8488593 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.1334. Min Act: -0.1700
Data Index: 8135643 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5396. Min Range: -7.5396
Max Act: 7.1334. Min Act: -0.1700
Data Index: 1068143 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19