Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 113 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.5360. Min Act: -0.1700
Data Index: 4272937 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.4735. Min Act: -0.1700
Data Index: 8015703 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.4735. Min Act: -0.1700
Data Index: 3892967 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.4110. Min Act: -0.1700
Data Index: 3946021 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.4110. Min Act: -0.1700
Data Index: 225434 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.4110. Min Act: -0.1700
Data Index: 3241782 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.4110. Min Act: -0.1700
Data Index: 3946020 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.3485. Min Act: -0.1700
Data Index: 8592557 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.3485. Min Act: -0.1700
Data Index: 3946019 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.3485. Min Act: -0.1700
Data Index: 753427 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.2860. Min Act: -0.1700
Data Index: 5786662 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.2547. Min Act: -0.1700
Data Index: 171203 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.2547. Min Act: -0.1700
Data Index: 1677315 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.2547. Min Act: -0.1700
Data Index: 2272796 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.2547. Min Act: -0.1700
Data Index: 5870936 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.2235. Min Act: -0.1700
Data Index: 2387132 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.2235. Min Act: -0.1700
Data Index: 3398784 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.2235. Min Act: -0.1700
Data Index: 488101 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.2235. Min Act: -0.1700
Data Index: 6103984 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5360. Min Range: -6.5360
Max Act: 6.2235. Min Act: -0.1700
Data Index: 4659091 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19