Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4025 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6935. Min Act: -0.1700
Data Index: 8310814 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6935. Min Act: -0.1700
Data Index: 8829056 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6622. Min Act: -0.1700
Data Index: 3787646 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6935. Min Act: -0.1700
Data Index: 1102379 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6622. Min Act: -0.1700
Data Index: 7056618 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6466. Min Act: -0.1700
Data Index: 4170287 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6309. Min Act: -0.1700
Data Index: 5270958 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5996. Min Act: -0.1700
Data Index: 1917303 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5840. Min Act: -0.1700
Data Index: 1596576 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5840. Min Act: -0.1700
Data Index: 7873295 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5683. Min Act: -0.1700
Data Index: 6355479 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5840. Min Act: -0.1700
Data Index: 7419903 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5527. Min Act: -0.1700
Data Index: 7490613 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5527. Min Act: -0.1700
Data Index: 3702311 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5527. Min Act: -0.1700
Data Index: 7557099 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5527. Min Act: -0.1700
Data Index: 6264381 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5527. Min Act: -0.1700
Data Index: 8637063 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5527. Min Act: -0.1700
Data Index: 5362160 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5527. Min Act: -0.1700
Data Index: 3464693 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5527. Min Act: -0.1700
Data Index: 6712566 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19