Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2674 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1015. Min Range: -9.1015
Max Act: 9.1015. Min Act: -0.1700
Data Index: 433871 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1015. Min Range: -9.1015
Max Act: 8.6640. Min Act: -0.1700
Data Index: 8696879 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1015. Min Range: -9.1015
Max Act: 8.6015. Min Act: -0.1700
Data Index: 6386871 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1015. Min Range: -9.1015
Max Act: 8.4140. Min Act: -0.1700
Data Index: 3936126 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1015. Min Range: -9.1015
Max Act: 8.3515. Min Act: -0.1700
Data Index: 1290598 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1015. Min Range: -9.1015
Max Act: 8.3515. Min Act: -0.1700
Data Index: 1240158 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1015. Min Range: -9.1015
Max Act: 8.1640. Min Act: -0.1700
Data Index: 833783 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1015. Min Range: -9.1015
Max Act: 8.1640. Min Act: -0.1700
Data Index: 2454363 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1015. Min Range: -9.1015
Max Act: 8.1015. Min Act: -0.1700
Data Index: 1531544 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1015. Min Range: -9.1015
Max Act: 7.9765. Min Act: -0.1700
Data Index: 4955278 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1015. Min Range: -9.1015
Max Act: 8.0390. Min Act: -0.1700
Data Index: 2385451 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1015. Min Range: -9.1015
Max Act: 7.9765. Min Act: -0.1700
Data Index: 966184 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1015. Min Range: -9.1015
Max Act: 7.9765. Min Act: -0.1700
Data Index: 8490816 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1015. Min Range: -9.1015
Max Act: 7.9765. Min Act: -0.1700
Data Index: 1342504 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1015. Min Range: -9.1015
Max Act: 7.9140. Min Act: -0.1700
Data Index: 3319052 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1015. Min Range: -9.1015
Max Act: 7.9140. Min Act: -0.1700
Data Index: 6423655 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1015. Min Range: -9.1015
Max Act: 7.9765. Min Act: -0.1700
Data Index: 1534918 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1015. Min Range: -9.1015
Max Act: 7.8515. Min Act: -0.1700
Data Index: 3065707 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1015. Min Range: -9.1015
Max Act: 7.8515. Min Act: -0.1700
Data Index: 2469948 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1015. Min Range: -9.1015
Max Act: 7.8515. Min Act: -0.1700
Data Index: 6684411 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19