Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.8547. Min Act: -0.1700
Data Index: 6297708 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.8234. Min Act: -0.1700
Data Index: 1036395 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.8234. Min Act: -0.1700
Data Index: 4825434 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.6359. Min Act: -0.1700
Data Index: 3866436 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.6047. Min Act: -0.1700
Data Index: 78915 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.5109. Min Act: -0.1700
Data Index: 8788075 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.5109. Min Act: -0.1700
Data Index: 5322263 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.4797. Min Act: -0.1700
Data Index: 949717 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.4797. Min Act: -0.1700
Data Index: 8616929 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.4484. Min Act: -0.1700
Data Index: 4364427 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.4484. Min Act: -0.1700
Data Index: 397179 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.3859. Min Act: -0.1700
Data Index: 4011678 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.3859. Min Act: -0.1700
Data Index: 4564316 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.3234. Min Act: -0.1700
Data Index: 4576288 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.3547. Min Act: -0.1700
Data Index: 2094805 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.3547. Min Act: -0.1700
Data Index: 714662 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.3547. Min Act: -0.1700
Data Index: 3618898 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.3234. Min Act: -0.1700
Data Index: 6516421 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.3234. Min Act: -0.1700
Data Index: 4079937 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8547. Min Range: -5.8547
Max Act: 5.3234. Min Act: -0.1700
Data Index: 930887 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19