Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3874 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.7073. Min Act: -0.1700
Data Index: 6707818 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.6761. Min Act: -0.1700
Data Index: 5277699 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.6448. Min Act: -0.1700
Data Index: 4011925 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.6761. Min Act: -0.1700
Data Index: 1479602 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.6761. Min Act: -0.1700
Data Index: 333102 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.6136. Min Act: -0.1700
Data Index: 127081 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.6136. Min Act: -0.1700
Data Index: 4017663 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.5511. Min Act: -0.1700
Data Index: 8745101 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.5511. Min Act: -0.1700
Data Index: 3806170 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.5198. Min Act: -0.1700
Data Index: 2678676 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.5198. Min Act: -0.1700
Data Index: 4434327 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.4886. Min Act: -0.1700
Data Index: 8698942 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.5198. Min Act: -0.1700
Data Index: 1159112 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.4886. Min Act: -0.1700
Data Index: 2746389 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.4886. Min Act: -0.1700
Data Index: 6331252 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.4886. Min Act: -0.1700
Data Index: 7166755 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.4886. Min Act: -0.1700
Data Index: 8477532 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.4261. Min Act: -0.1700
Data Index: 1540397 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.4886. Min Act: -0.1700
Data Index: 6765834 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7073. Min Range: -6.7073
Max Act: 6.4573. Min Act: -0.1700
Data Index: 3594971 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19