Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 103 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.8793. Min Act: -0.1700
Data Index: 6376276 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.7855. Min Act: -0.1700
Data Index: 6341994 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.1293. Min Act: -0.1700
Data Index: 7474627 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0980. Min Act: -0.1700
Data Index: 1042835 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0668. Min Act: -0.1700
Data Index: 875394 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8793. Min Range: -6.8793
Max Act: 6.0355. Min Act: -0.1700
Data Index: 6210687 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.8480. Min Act: -0.1700
Data Index: 176081 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.8480. Min Act: -0.1700
Data Index: 2387286 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.7855. Min Act: -0.1700
Data Index: 3789283 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.7855. Min Act: -0.1700
Data Index: 4002325 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.7855. Min Act: -0.1700
Data Index: 2462468 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.7230. Min Act: -0.1700
Data Index: 2136192 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.7230. Min Act: -0.1700
Data Index: 209842 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.6918. Min Act: -0.1700
Data Index: 5865677 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.6605. Min Act: -0.1700
Data Index: 5954102 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.6605. Min Act: -0.1700
Data Index: 112238 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.6293. Min Act: -0.1700
Data Index: 4785427 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.5980. Min Act: -0.1700
Data Index: 5266936 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.6293. Min Act: -0.1700
Data Index: 5344250 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8793. Min Range: -6.8793
Max Act: 5.5980. Min Act: -0.1700
Data Index: 2265809 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19