Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4354 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1131. Min Range: -6.1131
Max Act: 6.1131. Min Act: -0.1700
Data Index: 8705732 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1131. Min Range: -6.1131
Max Act: 6.0819. Min Act: -0.1700
Data Index: 5020894 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1131. Min Range: -6.1131
Max Act: 6.0506. Min Act: -0.1700
Data Index: 8542662 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1131. Min Range: -6.1131
Max Act: 6.0506. Min Act: -0.1700
Data Index: 7744144 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1131. Min Range: -6.1131
Max Act: 6.0819. Min Act: -0.1700
Data Index: 7525512 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.9881. Min Act: -0.1700
Data Index: 4846984 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.9569. Min Act: -0.1700
Data Index: 864966 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.9881. Min Act: -0.1700
Data Index: 842490 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8631. Min Act: -0.1700
Data Index: 2592393 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8631. Min Act: -0.1700
Data Index: 135050 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8631. Min Act: -0.1700
Data Index: 3331546 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8631. Min Act: -0.1700
Data Index: 4165769 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8631. Min Act: -0.1700
Data Index: 5518570 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8319. Min Act: -0.1700
Data Index: 6263413 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8319. Min Act: -0.1700
Data Index: 921762 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8319. Min Act: -0.1700
Data Index: 8650712 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8319. Min Act: -0.1700
Data Index: 8376538 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8006. Min Act: -0.1700
Data Index: 8611046 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8006. Min Act: -0.1700
Data Index: 2855726 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.7694. Min Act: -0.1700
Data Index: 5867707 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19