Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.3443. Min Act: -0.1700
Data Index: 8366321 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.1256. Min Act: -0.1700
Data Index: 8645663 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0943. Min Act: -0.1700
Data Index: 6847087 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0943. Min Act: -0.1700
Data Index: 665855 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0631. Min Act: -0.1700
Data Index: 1108575 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.9068. Min Act: -0.1700
Data Index: 4817071 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.9068. Min Act: -0.1700
Data Index: 1106659 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.8756. Min Act: -0.1700
Data Index: 7105156 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.8756. Min Act: -0.1700
Data Index: 2714605 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.8756. Min Act: -0.1700
Data Index: 6505256 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.8443. Min Act: -0.1700
Data Index: 3046735 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.8756. Min Act: -0.1700
Data Index: 8674577 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.8131. Min Act: -0.1700
Data Index: 3685009 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.8131. Min Act: -0.1700
Data Index: 8117413 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.8131. Min Act: -0.1700
Data Index: 5397861 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.8131. Min Act: -0.1700
Data Index: 5381021 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.8131. Min Act: -0.1700
Data Index: 1115205 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.8131. Min Act: -0.1700
Data Index: 7724184 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.7818. Min Act: -0.1700
Data Index: 8533169 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3443. Min Range: -5.3443
Max Act: 4.7818. Min Act: -0.1700
Data Index: 3494981 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19