Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.8411. Min Act: -0.1700
Data Index: 1424938 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.8093. Min Act: -0.1700
Data Index: 7107590 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.8093. Min Act: -0.1700
Data Index: 2632309 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7934. Min Act: -0.1700
Data Index: 1027955 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7615. Min Act: -0.1700
Data Index: 5363400 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7775. Min Act: -0.1700
Data Index: 414471 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7775. Min Act: -0.1700
Data Index: 8202808 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7456. Min Act: -0.1700
Data Index: 8737391 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7456. Min Act: -0.1700
Data Index: 2345858 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7456. Min Act: -0.1700
Data Index: 4463833 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7615. Min Act: -0.1700
Data Index: 6403399 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7456. Min Act: -0.1700
Data Index: 5638032 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7456. Min Act: -0.1700
Data Index: 3718315 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7615. Min Act: -0.1700
Data Index: 840852 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7456. Min Act: -0.1700
Data Index: 6633322 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7296. Min Act: -0.1700
Data Index: 5635515 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7456. Min Act: -0.1700
Data Index: 771919 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7296. Min Act: -0.1700
Data Index: 5671893 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7296. Min Act: -0.1700
Data Index: 7747504 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7296. Min Act: -0.1700
Data Index: 1116018 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19