Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4017 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1482. Min Range: -2.1482
Max Act: 2.1482. Min Act: -0.1700
Data Index: 6494782 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1482. Min Range: -2.1482
Max Act: 2.0309. Min Act: -0.1700
Data Index: 959718 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.9971. Min Act: -0.1700
Data Index: 4371362 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.9802. Min Act: -0.1700
Data Index: 2489937 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.9802. Min Act: -0.1700
Data Index: 4651086 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.9463. Min Act: -0.1700
Data Index: 6468001 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.9463. Min Act: -0.1700
Data Index: 6842263 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.9293. Min Act: -0.1700
Data Index: 410906 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.9123. Min Act: -0.1700
Data Index: 5231752 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.9463. Min Act: -0.1700
Data Index: 3841445 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.9123. Min Act: -0.1700
Data Index: 5025379 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.9123. Min Act: -0.1700
Data Index: 6551044 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.9123. Min Act: -0.1700
Data Index: 8404523 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.9123. Min Act: -0.1700
Data Index: 7327624 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.8952. Min Act: -0.1700
Data Index: 4282642 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.8781. Min Act: -0.1700
Data Index: 1384451 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.8952. Min Act: -0.1700
Data Index: 7526388 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.8952. Min Act: -0.1700
Data Index: 7752317 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.8781. Min Act: -0.1700
Data Index: 6230598 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1482. Min Range: -2.1482
Max Act: 1.8781. Min Act: -0.1700
Data Index: 1954212 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19