Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.9465. Min Act: -0.1700
Data Index: 4114924 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.8840. Min Act: -0.1700
Data Index: 8174953 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.5090. Min Act: -0.1700
Data Index: 2703402 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.4465. Min Act: -0.1700
Data Index: 6389376 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.4465. Min Act: -0.1700
Data Index: 8664693 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.5090. Min Act: -0.1700
Data Index: 4740305 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.4465. Min Act: -0.1700
Data Index: 2661753 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.5090. Min Act: -0.1700
Data Index: 8526506 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.3840. Min Act: -0.1700
Data Index: 4753237 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.3215. Min Act: -0.1700
Data Index: 8644680 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.3840. Min Act: -0.1700
Data Index: 171445 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.3215. Min Act: -0.1700
Data Index: 3547719 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.3215. Min Act: -0.1700
Data Index: 1719036 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.3215. Min Act: -0.1700
Data Index: 2063968 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.3215. Min Act: -0.1700
Data Index: 8543151 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.3215. Min Act: -0.1700
Data Index: 6702975 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.3215. Min Act: -0.1700
Data Index: 1771084 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.3215. Min Act: -0.1700
Data Index: 1472414 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.3215. Min Act: -0.1700
Data Index: 4984823 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9465. Min Range: -10.9465
Max Act: 10.2590. Min Act: -0.1700
Data Index: 7463410 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19