Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6655. Min Range: -5.6655
Max Act: 5.6655. Min Act: -0.1700
Data Index: 1220149 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6655. Min Range: -5.6655
Max Act: 5.4468. Min Act: -0.1700
Data Index: 8745456 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6655. Min Range: -5.6655
Max Act: 5.1030. Min Act: -0.1700
Data Index: 2716790 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6655. Min Range: -5.6655
Max Act: 5.1030. Min Act: -0.1700
Data Index: 4906774 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6655. Min Range: -5.6655
Max Act: 5.0093. Min Act: -0.1700
Data Index: 901738 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6655. Min Range: -5.6655
Max Act: 5.0405. Min Act: -0.1700
Data Index: 4508212 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6655. Min Range: -5.6655
Max Act: 5.0093. Min Act: -0.1700
Data Index: 5294312 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.9468. Min Act: -0.1700
Data Index: 4420707 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.9155. Min Act: -0.1700
Data Index: 2137066 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.9155. Min Act: -0.1700
Data Index: 4629510 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.8843. Min Act: -0.1700
Data Index: 46490 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.8843. Min Act: -0.1700
Data Index: 5916241 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.8530. Min Act: -0.1700
Data Index: 6193049 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.8218. Min Act: -0.1700
Data Index: 3209650 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.8218. Min Act: -0.1700
Data Index: 6827529 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.8218. Min Act: -0.1700
Data Index: 6190059 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.7905. Min Act: -0.1700
Data Index: 7170042 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.7905. Min Act: -0.1700
Data Index: 7455956 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.7905. Min Act: -0.1700
Data Index: 7406262 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6655. Min Range: -5.6655
Max Act: 4.7593. Min Act: -0.1700
Data Index: 768251 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19