Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3814 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.9945. Min Act: -0.1700
Data Index: 2390126 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.4320. Min Act: -0.1700
Data Index: 1177878 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.2757. Min Act: -0.1700
Data Index: 1075291 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.1820. Min Act: -0.1700
Data Index: 8787479 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.1507. Min Act: -0.1700
Data Index: 5440370 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.1195. Min Act: -0.1700
Data Index: 1894097 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.1195. Min Act: -0.1700
Data Index: 3051662 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.1195. Min Act: -0.1700
Data Index: 1550970 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.1195. Min Act: -0.1700
Data Index: 6490021 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.0570. Min Act: -0.1700
Data Index: 4739036 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.0570. Min Act: -0.1700
Data Index: 6625308 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9945. Min Range: -6.9945
Max Act: 5.9945. Min Act: -0.1700
Data Index: 1330996 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.0257. Min Act: -0.1700
Data Index: 2306091 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.0257. Min Act: -0.1700
Data Index: 1323718 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.0257. Min Act: -0.1700
Data Index: 5820745 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.0570. Min Act: -0.1700
Data Index: 1719162 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9945. Min Range: -6.9945
Max Act: 6.0257. Min Act: -0.1700
Data Index: 5486525 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9945. Min Range: -6.9945
Max Act: 5.9945. Min Act: -0.1700
Data Index: 4647542 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9945. Min Range: -6.9945
Max Act: 5.9945. Min Act: -0.1700
Data Index: 484990 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9945. Min Range: -6.9945
Max Act: 5.9945. Min Act: -0.1700
Data Index: 110372 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19