Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6391 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.5756. Min Act: -0.1700
Data Index: 4608317 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.5131. Min Act: -0.1700
Data Index: 8226004 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.5443. Min Act: -0.1700
Data Index: 830477 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.5443. Min Act: -0.1700
Data Index: 1088846 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.4818. Min Act: -0.1700
Data Index: 5337877 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.3881. Min Act: -0.1700
Data Index: 8412804 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.3568. Min Act: -0.1700
Data Index: 5925634 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.3568. Min Act: -0.1700
Data Index: 7534518 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.3568. Min Act: -0.1700
Data Index: 2396836 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.3256. Min Act: -0.1700
Data Index: 4458713 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.2943. Min Act: -0.1700
Data Index: 8412803 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.2943. Min Act: -0.1700
Data Index: 838333 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.2630. Min Act: -0.1700
Data Index: 2481936 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.2630. Min Act: -0.1700
Data Index: 4707450 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.2630. Min Act: -0.1700
Data Index: 3047593 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.2630. Min Act: -0.1700
Data Index: 3053913 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.2318. Min Act: -0.1700
Data Index: 6561706 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.2630. Min Act: -0.1700
Data Index: 2785612 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.2318. Min Act: -0.1700
Data Index: 6348303 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5756. Min Range: -4.5756
Max Act: 4.2318. Min Act: -0.1700
Data Index: 5231742 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19