Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4212 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7709. Min Range: -8.7709
Max Act: 8.7709. Min Act: -0.1700
Data Index: 2501206 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.8021. Min Act: -0.1700
Data Index: 6713234 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.6771. Min Act: -0.1700
Data Index: 8727139 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.7084. Min Act: -0.1700
Data Index: 2485360 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.6771. Min Act: -0.1700
Data Index: 7624167 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.6771. Min Act: -0.1700
Data Index: 3395796 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.5834. Min Act: -0.1700
Data Index: 627093 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.5834. Min Act: -0.1700
Data Index: 18979 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.5521. Min Act: -0.1700
Data Index: 1588759 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.5521. Min Act: -0.1700
Data Index: 4012878 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.4271. Min Act: -0.1700
Data Index: 7857297 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.4271. Min Act: -0.1700
Data Index: 6583347 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.3959. Min Act: -0.1700
Data Index: 1297201 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.3959. Min Act: -0.1700
Data Index: 6146866 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.3646. Min Act: -0.1700
Data Index: 570107 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.3959. Min Act: -0.1700
Data Index: 3760402 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.3646. Min Act: -0.1700
Data Index: 3078254 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.3646. Min Act: -0.1700
Data Index: 7406521 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.3334. Min Act: -0.1700
Data Index: 4564154 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7709. Min Range: -8.7709
Max Act: 7.3021. Min Act: -0.1700
Data Index: 6416170 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19