Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3895 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2949. Min Range: -6.2949
Max Act: 6.2949. Min Act: -0.1700
Data Index: 7628156 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2949. Min Range: -6.2949
Max Act: 6.2949. Min Act: -0.1700
Data Index: 8779266 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2949. Min Range: -6.2949
Max Act: 6.2011. Min Act: -0.1700
Data Index: 7651767 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2949. Min Range: -6.2949
Max Act: 6.1386. Min Act: -0.1700
Data Index: 1989820 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2949. Min Range: -6.2949
Max Act: 6.1074. Min Act: -0.1700
Data Index: 1339398 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2949. Min Range: -6.2949
Max Act: 6.0136. Min Act: -0.1700
Data Index: 2477942 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.9511. Min Act: -0.1700
Data Index: 1198057 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.9511. Min Act: -0.1700
Data Index: 6305646 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.9511. Min Act: -0.1700
Data Index: 4530854 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.9199. Min Act: -0.1700
Data Index: 5191381 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.8886. Min Act: -0.1700
Data Index: 6848802 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.9199. Min Act: -0.1700
Data Index: 6977207 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.8574. Min Act: -0.1700
Data Index: 7457656 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.8261. Min Act: -0.1700
Data Index: 5026558 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.8261. Min Act: -0.1700
Data Index: 3825155 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.8261. Min Act: -0.1700
Data Index: 2379164 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.7949. Min Act: -0.1700
Data Index: 8104960 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.8261. Min Act: -0.1700
Data Index: 8417546 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.7949. Min Act: -0.1700
Data Index: 7304176 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2949. Min Range: -6.2949
Max Act: 5.7949. Min Act: -0.1700
Data Index: 2814828 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19