Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.1968. Min Act: -0.1700
Data Index: 3463729 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.1302. Min Act: -0.1700
Data Index: 3009089 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.1135. Min Act: -0.1700
Data Index: 7237339 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0800. Min Act: -0.1700
Data Index: 4760551 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0800. Min Act: -0.1699
Data Index: 8702445 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0632. Min Act: -0.1700
Data Index: 2318181 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0296. Min Act: -0.1699
Data Index: 7456072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0296. Min Act: -0.1700
Data Index: 5670728 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0296. Min Act: -0.1700
Data Index: 5163393 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0296. Min Act: -0.1700
Data Index: 2642036 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0464. Min Act: -0.1700
Data Index: 6242792 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0127. Min Act: -0.1700
Data Index: 8525396 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0127. Min Act: -0.1700
Data Index: 7284346 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0127. Min Act: -0.1700
Data Index: 3463728 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0127. Min Act: -0.1700
Data Index: 1825028 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1968. Min Range: -2.1968
Max Act: 2.0127. Min Act: -0.1700
Data Index: 6647442 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1968. Min Range: -2.1968
Max Act: 1.9958. Min Act: -0.1700
Data Index: 7294543 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1968. Min Range: -2.1968
Max Act: 1.9958. Min Act: -0.1700
Data Index: 5522535 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1968. Min Range: -2.1968
Max Act: 1.9958. Min Act: -0.1700
Data Index: 5606974 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1968. Min Range: -2.1968
Max Act: 1.9958. Min Act: -0.1700
Data Index: 3400170 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19