Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.5832. Min Act: -0.1700
Data Index: 3998715 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.5207. Min Act: -0.1700
Data Index: 6468683 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3332. Min Act: -0.1700
Data Index: 4984621 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3332. Min Act: -0.1700
Data Index: 5356832 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3332. Min Act: -0.1699
Data Index: 5670125 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3019. Min Act: -0.1700
Data Index: 3259113 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3019. Min Act: -0.1700
Data Index: 3938995 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3019. Min Act: -0.1700
Data Index: 6830903 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3019. Min Act: -0.1700
Data Index: 1329315 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3019. Min Act: -0.1700
Data Index: 6607839 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3019. Min Act: -0.1700
Data Index: 1311313 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3019. Min Act: -0.1700
Data Index: 3128706 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3019. Min Act: -0.1699
Data Index: 6394339 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3019. Min Act: -0.1700
Data Index: 4394988 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3019. Min Act: -0.1700
Data Index: 8052883 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.3019. Min Act: -0.1700
Data Index: 3957110 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.2707. Min Act: -0.1700
Data Index: 1201070 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.2707. Min Act: -0.1700
Data Index: 2674255 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.2707. Min Act: -0.1700
Data Index: 6169661 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5832. Min Range: -5.5832
Max Act: 5.2707. Min Act: -0.1700
Data Index: 507796 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19