Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2509 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.8621. Min Act: -0.1700
Data Index: 6030480 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.6744. Min Act: -0.1700
Data Index: 4035840 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.6588. Min Act: -0.1700
Data Index: 1644991 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.6588. Min Act: -0.1700
Data Index: 5232767 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.6431. Min Act: -0.1700
Data Index: 103220 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.6275. Min Act: -0.1700
Data Index: 2261436 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.6431. Min Act: -0.1700
Data Index: 8221570 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.6275. Min Act: -0.1700
Data Index: 5781548 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.6275. Min Act: -0.1700
Data Index: 6982943 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.5962. Min Act: -0.1700
Data Index: 8005028 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.5962. Min Act: -0.1700
Data Index: 3766772 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.5962. Min Act: -0.1700
Data Index: 5366534 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.5649. Min Act: -0.1700
Data Index: 8745668 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.5962. Min Act: -0.1700
Data Index: 3664349 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.5962. Min Act: -0.1700
Data Index: 6990255 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.6118. Min Act: -0.1700
Data Index: 2517981 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.5962. Min Act: -0.1700
Data Index: 2694 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.5962. Min Act: -0.1700
Data Index: 1455760 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.5805. Min Act: -0.1700
Data Index: 6048259 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8621. Min Range: -3.8621
Max Act: 3.5805. Min Act: -0.1700
Data Index: 7399287 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19