Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3965 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.5792. Min Act: -0.1700
Data Index: 3802966 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.5480. Min Act: -0.1700
Data Index: 1805075 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.3917. Min Act: -0.1700
Data Index: 7628535 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.3917. Min Act: -0.1700
Data Index: 5529476 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.3605. Min Act: -0.1700
Data Index: 6897865 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.3605. Min Act: -0.1700
Data Index: 5784093 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.3292. Min Act: -0.1700
Data Index: 2650655 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.3292. Min Act: -0.1700
Data Index: 2897067 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.3292. Min Act: -0.1700
Data Index: 7877233 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.2980. Min Act: -0.1700
Data Index: 1007797 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.2980. Min Act: -0.1700
Data Index: 4395613 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.2980. Min Act: -0.1700
Data Index: 7974845 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.2980. Min Act: -0.1700
Data Index: 1838114 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.2667. Min Act: -0.1700
Data Index: 6330851 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.2980. Min Act: -0.1700
Data Index: 6540687 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.2980. Min Act: -0.1700
Data Index: 3965204 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.2980. Min Act: -0.1700
Data Index: 6037676 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.2980. Min Act: -0.1700
Data Index: 5593095 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.2667. Min Act: -0.1700
Data Index: 518871 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5792. Min Range: -4.5792
Max Act: 4.2667. Min Act: -0.1700
Data Index: 5135101 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19