Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4093 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.6965. Min Act: -0.1700
Data Index: 8169406 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.6027. Min Act: -0.1700
Data Index: 5961276 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.6027. Min Act: -0.1700
Data Index: 7198 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.5715. Min Act: -0.1700
Data Index: 1348506 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.4777. Min Act: -0.1700
Data Index: 2755751 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.4777. Min Act: -0.1700
Data Index: 7940658 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.4777. Min Act: -0.1700
Data Index: 2767730 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.4465. Min Act: -0.1700
Data Index: 8601622 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.4465. Min Act: -0.1700
Data Index: 8524532 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.3840. Min Act: -0.1700
Data Index: 301357 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.4152. Min Act: -0.1700
Data Index: 3838172 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.4152. Min Act: -0.1700
Data Index: 5591601 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.4152. Min Act: -0.1700
Data Index: 2834985 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.3840. Min Act: -0.1700
Data Index: 7248784 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.3840. Min Act: -0.1700
Data Index: 1986295 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.3527. Min Act: -0.1700
Data Index: 6895812 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.3840. Min Act: -0.1700
Data Index: 6059932 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.3527. Min Act: -0.1700
Data Index: 3327959 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.3527. Min Act: -0.1700
Data Index: 7497741 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6965. Min Range: -4.6965
Max Act: 4.3215. Min Act: -0.1700
Data Index: 1567399 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19