Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.4263. Min Act: -0.1700
Data Index: 7628646 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3937. Min Act: -0.1700
Data Index: 5221567 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3937. Min Act: -0.1700
Data Index: 742684 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3773. Min Act: -0.1700
Data Index: 5781948 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3446. Min Act: -0.1700
Data Index: 8497884 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3282. Min Act: -0.1700
Data Index: 3350528 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3282. Min Act: -0.1700
Data Index: 4094509 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3282. Min Act: -0.1700
Data Index: 827065 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3446. Min Act: -0.1699
Data Index: 784161 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3118. Min Act: -0.1700
Data Index: 6106768 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3118. Min Act: -0.1700
Data Index: 6650257 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3118. Min Act: -0.1700
Data Index: 552493 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3118. Min Act: -0.1700
Data Index: 2239002 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3118. Min Act: -0.1700
Data Index: 2131717 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3118. Min Act: -0.1700
Data Index: 3628411 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3118. Min Act: -0.1700
Data Index: 176384 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3118. Min Act: -0.1700
Data Index: 3438798 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3118. Min Act: -0.1699
Data Index: 4630288 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.3118. Min Act: -0.1700
Data Index: 4955713 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4263. Min Range: -2.4263
Max Act: 2.2953. Min Act: -0.1700
Data Index: 2446500 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19