Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3798 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0164. Min Range: -1.0164
Max Act: 1.0164. Min Act: -0.1700
Data Index: 3631106 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.9816. Min Act: -0.1700
Data Index: 6339511 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.9471. Min Act: -0.1700
Data Index: 3690156 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.9299. Min Act: -0.1700
Data Index: 2462966 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.9127. Min Act: -0.1697
Data Index: 3154919 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.9299. Min Act: -0.1700
Data Index: 8055600 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.9127. Min Act: -0.1700
Data Index: 50676 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.9041. Min Act: -0.1700
Data Index: 7551518 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.8956. Min Act: -0.1700
Data Index: 1617631 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.9041. Min Act: -0.1700
Data Index: 6073163 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.8870. Min Act: -0.1700
Data Index: 1838013 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.8956. Min Act: -0.1700
Data Index: 7895987 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.8870. Min Act: -0.1700
Data Index: 6797560 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.8785. Min Act: -0.1700
Data Index: 2755219 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.8700. Min Act: -0.1700
Data Index: 6631555 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.8700. Min Act: -0.1700
Data Index: 3853101 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.8785. Min Act: -0.1700
Data Index: 5236607 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.8530. Min Act: -0.1693
Data Index: 1484415 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.8530. Min Act: -0.1699
Data Index: 1658658 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0164. Min Range: -1.0164
Max Act: 0.8615. Min Act: -0.1700
Data Index: 106451 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19