Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3043 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0576. Min Range: -10.0576
Max Act: 10.0576. Min Act: -0.1700
Data Index: 4200807 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.7451. Min Act: -0.1700
Data Index: 660236 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.4326. Min Act: -0.1700
Data Index: 1448980 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.3701. Min Act: -0.1700
Data Index: 6713203 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.3076. Min Act: -0.1700
Data Index: 1940614 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.3076. Min Act: -0.1700
Data Index: 946833 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.3076. Min Act: -0.1700
Data Index: 8423659 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.1826. Min Act: -0.1700
Data Index: 5002088 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.1826. Min Act: -0.1700
Data Index: 2752020 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.1826. Min Act: -0.1700
Data Index: 7391383 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.1201. Min Act: -0.1700
Data Index: 3563098 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.1201. Min Act: -0.1700
Data Index: 1150215 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.1201. Min Act: -0.1700
Data Index: 48149 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.0576. Min Act: -0.1700
Data Index: 3929224 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.0576. Min Act: -0.1700
Data Index: 684964 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0576. Min Range: -10.0576
Max Act: 9.0576. Min Act: -0.1700
Data Index: 997379 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0576. Min Range: -10.0576
Max Act: 8.9951. Min Act: -0.1700
Data Index: 263679 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0576. Min Range: -10.0576
Max Act: 8.9326. Min Act: -0.1700
Data Index: 8324474 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0576. Min Range: -10.0576
Max Act: 8.9326. Min Act: -0.1700
Data Index: 8310918 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0576. Min Range: -10.0576
Max Act: 8.9326. Min Act: -0.1700
Data Index: 7597344 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19