Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 768 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0549. Min Range: -8.0549
Max Act: 8.0549. Min Act: -0.1700
Data Index: 6629305 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.9299. Min Act: -0.1700
Data Index: 8679377 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.8674. Min Act: -0.1700
Data Index: 7907351 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.8361. Min Act: -0.1700
Data Index: 21430 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.8049. Min Act: -0.1700
Data Index: 3053754 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.7424. Min Act: -0.1700
Data Index: 383327 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.7424. Min Act: -0.1700
Data Index: 7692129 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.7111. Min Act: -0.1700
Data Index: 2396902 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.6799. Min Act: -0.1700
Data Index: 6319815 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.6799. Min Act: -0.1700
Data Index: 5974245 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.6799. Min Act: -0.1700
Data Index: 7594940 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.6486. Min Act: -0.1700
Data Index: 4971886 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.6486. Min Act: -0.1700
Data Index: 863778 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.6174. Min Act: -0.1700
Data Index: 8583403 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.5861. Min Act: -0.1700
Data Index: 3669092 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.5861. Min Act: -0.1700
Data Index: 6458318 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.5861. Min Act: -0.1700
Data Index: 1371513 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.6174. Min Act: -0.1700
Data Index: 8659051 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.5861. Min Act: -0.1700
Data Index: 7328077 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0549. Min Range: -8.0549
Max Act: 7.6174. Min Act: -0.1700
Data Index: 965431 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19