Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1981 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.3259. Min Act: -0.1700
Data Index: 1478154 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.3573. Min Act: -0.1700
Data Index: 4185511 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2788. Min Act: -0.1700
Data Index: 2263451 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2631. Min Act: -0.1700
Data Index: 5908128 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2317. Min Act: -0.1700
Data Index: 4330656 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2474. Min Act: -0.1700
Data Index: 3077786 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2474. Min Act: -0.1700
Data Index: 3813651 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2317. Min Act: -0.1700
Data Index: 3767579 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2002. Min Act: -0.1700
Data Index: 4570833 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1845. Min Act: -0.1700
Data Index: 7629629 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1845. Min Act: -0.1700
Data Index: 4559875 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1688. Min Act: -0.1700
Data Index: 8560624 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1688. Min Act: -0.1700
Data Index: 3047247 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1688. Min Act: -0.1700
Data Index: 7064111 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1530. Min Act: -0.1700
Data Index: 7308743 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1530. Min Act: -0.1700
Data Index: 4128947 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1373. Min Act: -0.1700
Data Index: 7404998 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1373. Min Act: -0.1700
Data Index: 101918 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1373. Min Act: -0.1700
Data Index: 4025579 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1373. Min Act: -0.1700
Data Index: 2519352 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19