Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 472 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.6450. Min Act: -0.1700
Data Index: 190538 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.6138. Min Act: -0.1700
Data Index: 8640970 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.5200. Min Act: -0.1700
Data Index: 5006084 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.4575. Min Act: -0.1700
Data Index: 8817821 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.4263. Min Act: -0.1700
Data Index: 4284049 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.4263. Min Act: -0.1700
Data Index: 8193015 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.4263. Min Act: -0.1700
Data Index: 6240018 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3950. Min Act: -0.1700
Data Index: 4146157 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3638. Min Act: -0.1700
Data Index: 2403387 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3325. Min Act: -0.1700
Data Index: 6143296 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3638. Min Act: -0.1700
Data Index: 5714579 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3325. Min Act: -0.1700
Data Index: 4961858 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3013. Min Act: -0.1700
Data Index: 2002066 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.2700. Min Act: -0.1700
Data Index: 890176 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.2388. Min Act: -0.1700
Data Index: 8302508 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.2700. Min Act: -0.1700
Data Index: 4923412 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.2388. Min Act: -0.1700
Data Index: 1657003 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.2388. Min Act: -0.1700
Data Index: 6588928 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.2075. Min Act: -0.1700
Data Index: 5159438 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.2075. Min Act: -0.1700
Data Index: 7136830 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19