Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3149 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.3844. Min Act: -0.1700
Data Index: 4165697 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.3687. Min Act: -0.1700
Data Index: 5980928 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.3844. Min Act: -0.1700
Data Index: 7686171 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.3530. Min Act: -0.1700
Data Index: 4135017 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.3373. Min Act: -0.1700
Data Index: 3039743 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.2745. Min Act: -0.1700
Data Index: 3238893 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.3059. Min Act: -0.1700
Data Index: 5254326 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.2588. Min Act: -0.1700
Data Index: 703280 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.2274. Min Act: -0.1700
Data Index: 1178708 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.2117. Min Act: -0.1700
Data Index: 493356 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.1960. Min Act: -0.1700
Data Index: 5065337 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.1960. Min Act: -0.1700
Data Index: 2889099 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.2117. Min Act: -0.1700
Data Index: 3277807 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.1645. Min Act: -0.1700
Data Index: 147535 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.1645. Min Act: -0.1700
Data Index: 3726114 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.1802. Min Act: -0.1700
Data Index: 3588157 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.1802. Min Act: -0.1700
Data Index: 1178709 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.1488. Min Act: -0.1700
Data Index: 4153199 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.1488. Min Act: -0.1700
Data Index: 2195571 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3844. Min Range: -3.3844
Max Act: 3.1645. Min Act: -0.1700
Data Index: 1592361 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19