Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2353 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.5193. Min Act: -0.1700
Data Index: 5160400 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.3631. Min Act: -0.1700
Data Index: 6069010 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.2381. Min Act: -0.1700
Data Index: 5743408 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.1756. Min Act: -0.1700
Data Index: 2237709 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.1756. Min Act: -0.1700
Data Index: 1535090 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.1131. Min Act: -0.1700
Data Index: 1973039 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.0506. Min Act: -0.1700
Data Index: 5930079 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.0193. Min Act: -0.1700
Data Index: 5666248 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.0193. Min Act: -0.1700
Data Index: 7650954 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.0193. Min Act: -0.1700
Data Index: 2519855 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9881. Min Act: -0.1700
Data Index: 6477007 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9568. Min Act: -0.1700
Data Index: 8079120 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9568. Min Act: -0.1700
Data Index: 6143388 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9256. Min Act: -0.1700
Data Index: 1468592 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9256. Min Act: -0.1700
Data Index: 6246571 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9256. Min Act: -0.1700
Data Index: 2527816 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.8943. Min Act: -0.1700
Data Index: 7489722 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.8631. Min Act: -0.1700
Data Index: 6729620 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.8943. Min Act: -0.1700
Data Index: 3820378 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.8943. Min Act: -0.1700
Data Index: 6274181 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19