Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.9944. Min Act: -0.1700
Data Index: 220211 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.9007. Min Act: -0.1700
Data Index: 5657880 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.8382. Min Act: -0.1700
Data Index: 5652912 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.7132. Min Act: -0.1700
Data Index: 6091013 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.6819. Min Act: -0.1700
Data Index: 829898 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.6819. Min Act: -0.1700
Data Index: 3300441 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.5882. Min Act: -0.1700
Data Index: 2594353 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.5569. Min Act: -0.1700
Data Index: 8541796 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.4632. Min Act: -0.1700
Data Index: 1883338 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.4632. Min Act: -0.1700
Data Index: 4501616 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.4632. Min Act: -0.1700
Data Index: 5440243 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.4319. Min Act: -0.1700
Data Index: 8752619 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.4632. Min Act: -0.1700
Data Index: 456170 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.4319. Min Act: -0.1700
Data Index: 701519 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.4319. Min Act: -0.1700
Data Index: 1298930 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.4319. Min Act: -0.1700
Data Index: 1676895 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.4319. Min Act: -0.1700
Data Index: 5697753 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.4007. Min Act: -0.1700
Data Index: 6273019 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.4007. Min Act: -0.1700
Data Index: 684354 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9944. Min Range: -5.9944
Max Act: 5.3694. Min Act: -0.1700
Data Index: 7087789 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19