Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1505. Min Range: -5.1505
Max Act: 5.1505. Min Act: -0.1700
Data Index: 4081206 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.9942. Min Act: -0.1700
Data Index: 1653514 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.9630. Min Act: -0.1700
Data Index: 958706 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.9317. Min Act: -0.1700
Data Index: 793303 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.8692. Min Act: -0.1700
Data Index: 1174537 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.8067. Min Act: -0.1700
Data Index: 2524342 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.8380. Min Act: -0.1700
Data Index: 7417985 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.7442. Min Act: -0.1700
Data Index: 1042581 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.7442. Min Act: -0.1700
Data Index: 8400920 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.7130. Min Act: -0.1700
Data Index: 4595614 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.6817. Min Act: -0.1700
Data Index: 4364330 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.6505. Min Act: -0.1700
Data Index: 3717679 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.7130. Min Act: -0.1700
Data Index: 3541138 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.6505. Min Act: -0.1700
Data Index: 4859676 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.6192. Min Act: -0.1700
Data Index: 6842071 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.6192. Min Act: -0.1700
Data Index: 2262762 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.6192. Min Act: -0.1700
Data Index: 5587748 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.6192. Min Act: -0.1700
Data Index: 6177597 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.6192. Min Act: -0.1700
Data Index: 5634064 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1505. Min Range: -5.1505
Max Act: 4.6192. Min Act: -0.1700
Data Index: 2957677 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19