Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 164 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5560. Min Range: -6.5560
Max Act: 6.5560. Min Act: -0.1700
Data Index: 3369915 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5560. Min Range: -6.5560
Max Act: 6.0560. Min Act: -0.1700
Data Index: 5574862 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.9935. Min Act: -0.1700
Data Index: 3495759 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.9935. Min Act: -0.1700
Data Index: 828849 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.9623. Min Act: -0.1700
Data Index: 5377387 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.9623. Min Act: -0.1700
Data Index: 1926564 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.9623. Min Act: -0.1700
Data Index: 7508837 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.9623. Min Act: -0.1700
Data Index: 6399821 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.9310. Min Act: -0.1700
Data Index: 8447135 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.9310. Min Act: -0.1700
Data Index: 6342799 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.8998. Min Act: -0.1700
Data Index: 1250207 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.8998. Min Act: -0.1700
Data Index: 538014 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.8998. Min Act: -0.1700
Data Index: 1938419 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.8685. Min Act: -0.1700
Data Index: 5051067 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.8373. Min Act: -0.1700
Data Index: 6145553 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.8373. Min Act: -0.1700
Data Index: 3557666 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.8060. Min Act: -0.1700
Data Index: 5713269 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.7435. Min Act: -0.1700
Data Index: 8560084 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.7123. Min Act: -0.1700
Data Index: 6630242 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5560. Min Range: -6.5560
Max Act: 5.7123. Min Act: -0.1700
Data Index: 6734532 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19