Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.7580. Min Act: -0.1700
Data Index: 5016891 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.6955. Min Act: -0.1700
Data Index: 5880702 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.6017. Min Act: -0.1700
Data Index: 4187065 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.3517. Min Act: -0.1700
Data Index: 7436442 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.3205. Min Act: -0.1700
Data Index: 2890965 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.3205. Min Act: -0.1700
Data Index: 2544612 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.2892. Min Act: -0.1700
Data Index: 5139928 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.3205. Min Act: -0.1700
Data Index: 8083233 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.2267. Min Act: -0.1700
Data Index: 4758873 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.2580. Min Act: -0.1700
Data Index: 5053090 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.1955. Min Act: -0.1700
Data Index: 8689979 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.2267. Min Act: -0.1700
Data Index: 1711332 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.1955. Min Act: -0.1700
Data Index: 2790216 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.1330. Min Act: -0.1700
Data Index: 4275093 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.1017. Min Act: -0.1700
Data Index: 7505511 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.1017. Min Act: -0.1700
Data Index: 1223818 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.0705. Min Act: -0.1700
Data Index: 2055172 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.0705. Min Act: -0.1700
Data Index: 7585358 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.0705. Min Act: -0.1700
Data Index: 3408555 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7580. Min Range: -6.7580
Max Act: 6.1017. Min Act: -0.1700
Data Index: 8017613 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19