Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.2871. Min Act: -0.1700
Data Index: 7914890 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.2246. Min Act: -0.1700
Data Index: 886226 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.2246. Min Act: -0.1700
Data Index: 6874064 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.2246. Min Act: -0.1700
Data Index: 2226594 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.1621. Min Act: -0.1700
Data Index: 3828474 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.0996. Min Act: -0.1700
Data Index: 7854477 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.0684. Min Act: -0.1700
Data Index: 5721114 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.0996. Min Act: -0.1700
Data Index: 6263989 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.0371. Min Act: -0.1700
Data Index: 3324731 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.0371. Min Act: -0.1700
Data Index: 8649771 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.0371. Min Act: -0.1700
Data Index: 2968234 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.0371. Min Act: -0.1700
Data Index: 4388430 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.0059. Min Act: -0.1700
Data Index: 6263988 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.0059. Min Act: -0.1700
Data Index: 1917739 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.0059. Min Act: -0.1700
Data Index: 936532 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.0059. Min Act: -0.1700
Data Index: 5469257 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2871. Min Range: -7.2871
Max Act: 6.9434. Min Act: -0.1700
Data Index: 1046358 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2871. Min Range: -7.2871
Max Act: 6.9746. Min Act: -0.1700
Data Index: 8701375 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2871. Min Range: -7.2871
Max Act: 6.9746. Min Act: -0.1700
Data Index: 4912629 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2871. Min Range: -7.2871
Max Act: 7.0059. Min Act: -0.1700
Data Index: 3131444 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19