Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 384 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.5247. Min Act: -0.1700
Data Index: 2536173 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4621. Min Act: -0.1700
Data Index: 367638 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4464. Min Act: -0.1700
Data Index: 639003 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4621. Min Act: -0.1700
Data Index: 43180 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4464. Min Act: -0.1700
Data Index: 4819652 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3837. Min Act: -0.1700
Data Index: 225021 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3994. Min Act: -0.1700
Data Index: 2649306 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3680. Min Act: -0.1700
Data Index: 7008848 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3680. Min Act: -0.1700
Data Index: 7793849 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3523. Min Act: -0.1700
Data Index: 191569 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3209. Min Act: -0.1700
Data Index: 8373427 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3209. Min Act: -0.1700
Data Index: 8708541 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3209. Min Act: -0.1700
Data Index: 7027064 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3209. Min Act: -0.1700
Data Index: 633215 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3052. Min Act: -0.1700
Data Index: 726992 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3052. Min Act: -0.1700
Data Index: 388375 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3052. Min Act: -0.1700
Data Index: 5469412 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3052. Min Act: -0.1700
Data Index: 3022668 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.2895. Min Act: -0.1700
Data Index: 2285100 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.3052. Min Act: -0.1700
Data Index: 6686034 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19