Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 605 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.8139. Min Act: -0.1700
Data Index: 3737323 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.7827. Min Act: -0.1700
Data Index: 3207702 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.7514. Min Act: -0.1700
Data Index: 3082482 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.7202. Min Act: -0.1700
Data Index: 4787544 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.7202. Min Act: -0.1700
Data Index: 2960819 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.7202. Min Act: -0.1700
Data Index: 2185233 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6889. Min Act: -0.1700
Data Index: 5114609 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6889. Min Act: -0.1700
Data Index: 3423214 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6889. Min Act: -0.1700
Data Index: 3259997 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6889. Min Act: -0.1700
Data Index: 572894 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6889. Min Act: -0.1700
Data Index: 207913 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6889. Min Act: -0.1700
Data Index: 2064092 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6577. Min Act: -0.1700
Data Index: 8254661 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6577. Min Act: -0.1699
Data Index: 1104181 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6577. Min Act: -0.1700
Data Index: 3376020 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6577. Min Act: -0.1700
Data Index: 2521135 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6264. Min Act: -0.1700
Data Index: 3086595 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6577. Min Act: -0.1700
Data Index: 544193 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6577. Min Act: -0.1700
Data Index: 2831636 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6577. Min Act: -0.1700
Data Index: 2947828 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19