Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.4215. Min Act: -0.1700
Data Index: 4596787 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.4059. Min Act: -0.1700
Data Index: 4682229 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.3902. Min Act: -0.1700
Data Index: 2339420 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.3431. Min Act: -0.1700
Data Index: 3057125 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.3274. Min Act: -0.1700
Data Index: 7867304 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2961. Min Act: -0.1700
Data Index: 8248638 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2961. Min Act: -0.1700
Data Index: 5425377 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2961. Min Act: -0.1700
Data Index: 2406286 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2961. Min Act: -0.1700
Data Index: 6415972 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2961. Min Act: -0.1700
Data Index: 5314178 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2961. Min Act: -0.1700
Data Index: 5576548 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2804. Min Act: -0.1700
Data Index: 3162977 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2804. Min Act: -0.1700
Data Index: 7452009 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2646. Min Act: -0.1700
Data Index: 8328572 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2646. Min Act: -0.1700
Data Index: 3371705 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2489. Min Act: -0.1700
Data Index: 8756637 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2489. Min Act: -0.1700
Data Index: 426685 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2489. Min Act: -0.1700
Data Index: 6543702 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2332. Min Act: -0.1700
Data Index: 1776760 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4215. Min Range: -3.4215
Max Act: 3.2175. Min Act: -0.1700
Data Index: 7297699 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19