Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4670 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1713. Min Range: -6.1713
Max Act: 6.1713. Min Act: -0.1700
Data Index: 488071 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.6088. Min Act: -0.1700
Data Index: 7054257 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.5151. Min Act: -0.1700
Data Index: 2303866 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.4838. Min Act: -0.1700
Data Index: 4716231 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.3901. Min Act: -0.1700
Data Index: 2040915 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.3901. Min Act: -0.1700
Data Index: 6355126 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.3588. Min Act: -0.1700
Data Index: 7930974 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.3588. Min Act: -0.1700
Data Index: 317179 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.3588. Min Act: -0.1700
Data Index: 1683303 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.3588. Min Act: -0.1700
Data Index: 2555492 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.3588. Min Act: -0.1700
Data Index: 6852660 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.3276. Min Act: -0.1700
Data Index: 2879886 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.2963. Min Act: -0.1700
Data Index: 754181 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.2963. Min Act: -0.1700
Data Index: 3092643 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.3276. Min Act: -0.1700
Data Index: 7888626 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.2963. Min Act: -0.1700
Data Index: 6852661 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.2963. Min Act: -0.1700
Data Index: 7297269 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.2963. Min Act: -0.1700
Data Index: 1212749 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.2651. Min Act: -0.1700
Data Index: 3751986 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1713. Min Range: -6.1713
Max Act: 5.2338. Min Act: -0.1700
Data Index: 89163 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19