Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4855 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.9037. Min Act: -0.1700
Data Index: 283029 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.9037. Min Act: -0.1700
Data Index: 3059095 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.6849. Min Act: -0.1700
Data Index: 4362219 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.6849. Min Act: -0.1700
Data Index: 1731068 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.6537. Min Act: -0.1700
Data Index: 2274953 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.6537. Min Act: -0.1700
Data Index: 3969926 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.6537. Min Act: -0.1700
Data Index: 3489781 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.5912. Min Act: -0.1700
Data Index: 4694068 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.5912. Min Act: -0.1700
Data Index: 1255942 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.5599. Min Act: -0.1700
Data Index: 3330075 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.5287. Min Act: -0.1700
Data Index: 6903547 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.4349. Min Act: -0.1700
Data Index: 1053091 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.4037. Min Act: -0.1700
Data Index: 4162697 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.4037. Min Act: -0.1700
Data Index: 7108211 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.4037. Min Act: -0.1700
Data Index: 2223115 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.3724. Min Act: -0.1700
Data Index: 282999 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.3412. Min Act: -0.1700
Data Index: 7919765 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.3099. Min Act: -0.1700
Data Index: 8393274 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.2787. Min Act: -0.1700
Data Index: 8173658 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9037. Min Range: -7.9037
Max Act: 7.2787. Min Act: -0.1700
Data Index: 2317360 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19