Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2477 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.8956. Min Act: -0.1700
Data Index: 8518990 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.8330. Min Act: -0.1700
Data Index: 4615618 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.8330. Min Act: -0.1700
Data Index: 6792870 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.8330. Min Act: -0.1700
Data Index: 5982841 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.8018. Min Act: -0.1700
Data Index: 7525379 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.7705. Min Act: -0.1700
Data Index: 2557240 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.7705. Min Act: -0.1700
Data Index: 5001129 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.7392. Min Act: -0.1700
Data Index: 2491632 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6766. Min Act: -0.1700
Data Index: 2229747 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.7079. Min Act: -0.1700
Data Index: 1671279 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.7079. Min Act: -0.1700
Data Index: 568876 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6454. Min Act: -0.1700
Data Index: 5001123 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6454. Min Act: -0.1700
Data Index: 2405990 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6454. Min Act: -0.1700
Data Index: 1903331 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6454. Min Act: -0.1700
Data Index: 5672602 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.5828. Min Act: -0.1700
Data Index: 7920969 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.6141. Min Act: -0.1700
Data Index: 7945965 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.5828. Min Act: -0.1700
Data Index: 3927021 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.5828. Min Act: -0.1700
Data Index: 5255350 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8956. Min Range: -3.8956
Max Act: 3.5514. Min Act: -0.1700
Data Index: 8024324 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19