Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1296 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0414. Min Range: -7.0414
Max Act: 7.0414. Min Act: -0.1700
Data Index: 1599013 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.6664. Min Act: -0.1700
Data Index: 1243991 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.4476. Min Act: -0.1700
Data Index: 5729138 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.4476. Min Act: -0.1700
Data Index: 4872061 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.4164. Min Act: -0.1700
Data Index: 4107725 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.3851. Min Act: -0.1700
Data Index: 798791 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.2914. Min Act: -0.1700
Data Index: 6085842 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.2914. Min Act: -0.1700
Data Index: 1999877 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.2601. Min Act: -0.1700
Data Index: 5044856 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.2289. Min Act: -0.1700
Data Index: 8009021 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.1976. Min Act: -0.1700
Data Index: 4576578 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.1976. Min Act: -0.1700
Data Index: 3670414 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.1976. Min Act: -0.1700
Data Index: 7564274 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.1351. Min Act: -0.1700
Data Index: 835670 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.1039. Min Act: -0.1700
Data Index: 4140146 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.1664. Min Act: -0.1700
Data Index: 288252 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.1039. Min Act: -0.1700
Data Index: 251752 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.1351. Min Act: -0.1700
Data Index: 22288 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.1039. Min Act: -0.1700
Data Index: 3579681 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0414. Min Range: -7.0414
Max Act: 6.0726. Min Act: -0.1700
Data Index: 1954759 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19