Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1866 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0623. Min Range: -4.0623
Max Act: 4.0623. Min Act: -0.1700
Data Index: 2218632 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9373. Min Act: -0.1700
Data Index: 8171992 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8747. Min Act: -0.1700
Data Index: 2002409 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9060. Min Act: -0.1700
Data Index: 7336685 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9060. Min Act: -0.1700
Data Index: 2543759 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8747. Min Act: -0.1700
Data Index: 7623792 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.9060. Min Act: -0.1700
Data Index: 6535292 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8747. Min Act: -0.1700
Data Index: 1448389 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8435. Min Act: -0.1700
Data Index: 7246659 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8747. Min Act: -0.1700
Data Index: 5095717 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8747. Min Act: -0.1700
Data Index: 7712854 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8747. Min Act: -0.1700
Data Index: 5635213 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8435. Min Act: -0.1700
Data Index: 1628449 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8435. Min Act: -0.1700
Data Index: 1606859 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8122. Min Act: -0.1700
Data Index: 692938 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8122. Min Act: -0.1700
Data Index: 4737351 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.7809. Min Act: -0.1700
Data Index: 6093813 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8122. Min Act: -0.1700
Data Index: 2306299 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8122. Min Act: -0.1700
Data Index: 4071649 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0623. Min Range: -4.0623
Max Act: 3.8122. Min Act: -0.1700
Data Index: 5083945 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19