Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6909. Min Range: -7.6909
Max Act: 7.6909. Min Act: -0.1700
Data Index: 2424436 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6909. Min Range: -7.6909
Max Act: 7.6284. Min Act: -0.1700
Data Index: 74505 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6909. Min Range: -7.6909
Max Act: 7.2534. Min Act: -0.1700
Data Index: 8172902 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6909. Min Range: -7.6909
Max Act: 7.1597. Min Act: -0.1700
Data Index: 1276556 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6909. Min Range: -7.6909
Max Act: 7.1284. Min Act: -0.1700
Data Index: 6210674 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6909. Min Range: -7.6909
Max Act: 7.0659. Min Act: -0.1700
Data Index: 8113649 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6909. Min Range: -7.6909
Max Act: 7.0347. Min Act: -0.1700
Data Index: 4564169 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6909. Min Range: -7.6909
Max Act: 7.0347. Min Act: -0.1700
Data Index: 6884676 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6909. Min Range: -7.6909
Max Act: 7.0034. Min Act: -0.1700
Data Index: 4804692 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6909. Min Range: -7.6909
Max Act: 6.9409. Min Act: -0.1700
Data Index: 2125516 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6909. Min Range: -7.6909
Max Act: 6.9722. Min Act: -0.1700
Data Index: 4689654 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6909. Min Range: -7.6909
Max Act: 6.9722. Min Act: -0.1700
Data Index: 8548491 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6909. Min Range: -7.6909
Max Act: 6.9097. Min Act: -0.1700
Data Index: 5904500 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6909. Min Range: -7.6909
Max Act: 6.9097. Min Act: -0.1700
Data Index: 162604 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6909. Min Range: -7.6909
Max Act: 6.8784. Min Act: -0.1700
Data Index: 8248832 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6909. Min Range: -7.6909
Max Act: 6.8784. Min Act: -0.1700
Data Index: 5850489 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6909. Min Range: -7.6909
Max Act: 6.8784. Min Act: -0.1700
Data Index: 6565022 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6909. Min Range: -7.6909
Max Act: 6.8159. Min Act: -0.1700
Data Index: 8077542 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6909. Min Range: -7.6909
Max Act: 6.8472. Min Act: -0.1700
Data Index: 5257217 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6909. Min Range: -7.6909
Max Act: 6.8159. Min Act: -0.1700
Data Index: 3848698 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19