Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4845 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1621. Min Range: -5.1621
Max Act: 5.1621. Min Act: -0.1700
Data Index: 7128845 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1621. Min Range: -5.1621
Max Act: 5.1621. Min Act: -0.1700
Data Index: 7039188 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1621. Min Range: -5.1621
Max Act: 5.1308. Min Act: -0.1700
Data Index: 2460260 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1621. Min Range: -5.1621
Max Act: 5.0996. Min Act: -0.1700
Data Index: 1352861 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1621. Min Range: -5.1621
Max Act: 5.0683. Min Act: -0.1700
Data Index: 5951600 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1621. Min Range: -5.1621
Max Act: 5.0371. Min Act: -0.1700
Data Index: 6647314 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1621. Min Range: -5.1621
Max Act: 5.0371. Min Act: -0.1700
Data Index: 2830631 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1621. Min Range: -5.1621
Max Act: 5.0058. Min Act: -0.1700
Data Index: 5178671 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1621. Min Range: -5.1621
Max Act: 4.9746. Min Act: -0.1700
Data Index: 2312674 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1621. Min Range: -5.1621
Max Act: 4.9746. Min Act: -0.1700
Data Index: 4097738 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1621. Min Range: -5.1621
Max Act: 4.9746. Min Act: -0.1700
Data Index: 7208729 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1621. Min Range: -5.1621
Max Act: 4.9433. Min Act: -0.1700
Data Index: 7356120 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1621. Min Range: -5.1621
Max Act: 4.9433. Min Act: -0.1700
Data Index: 3695725 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1621. Min Range: -5.1621
Max Act: 4.9746. Min Act: -0.1700
Data Index: 958092 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1621. Min Range: -5.1621
Max Act: 4.9433. Min Act: -0.1700
Data Index: 1547532 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1621. Min Range: -5.1621
Max Act: 4.9433. Min Act: -0.1700
Data Index: 1804271 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1621. Min Range: -5.1621
Max Act: 4.9746. Min Act: -0.1700
Data Index: 4783893 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1621. Min Range: -5.1621
Max Act: 4.9433. Min Act: -0.1700
Data Index: 132931 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1621. Min Range: -5.1621
Max Act: 4.9121. Min Act: -0.1700
Data Index: 6719959 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1621. Min Range: -5.1621
Max Act: 4.9121. Min Act: -0.1700
Data Index: 43028 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19