Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4757 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3030. Min Range: -7.3030
Max Act: 7.3030. Min Act: -0.1700
Data Index: 2476583 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3030. Min Range: -7.3030
Max Act: 7.2718. Min Act: -0.1700
Data Index: 8019078 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3030. Min Range: -7.3030
Max Act: 7.1468. Min Act: -0.1700
Data Index: 8511418 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.9593. Min Act: -0.1700
Data Index: 7547238 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.8655. Min Act: -0.1700
Data Index: 6823829 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.8030. Min Act: -0.1700
Data Index: 6118453 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.7718. Min Act: -0.1700
Data Index: 4003079 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.7405. Min Act: -0.1700
Data Index: 2623582 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.7405. Min Act: -0.1700
Data Index: 6325842 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.7093. Min Act: -0.1700
Data Index: 3648934 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.6468. Min Act: -0.1700
Data Index: 6280910 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.6155. Min Act: -0.1700
Data Index: 318774 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.5843. Min Act: -0.1700
Data Index: 1055349 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.5218. Min Act: -0.1700
Data Index: 2383762 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.5530. Min Act: -0.1700
Data Index: 6930376 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.5530. Min Act: -0.1700
Data Index: 5860450 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.5530. Min Act: -0.1700
Data Index: 981077 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.5530. Min Act: -0.1700
Data Index: 4011745 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.5530. Min Act: -0.1700
Data Index: 2592089 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3030. Min Range: -7.3030
Max Act: 6.5530. Min Act: -0.1700
Data Index: 5953387 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19