Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2626 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8998. Min Act: -0.1700
Data Index: 240582 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8998. Min Act: -0.1700
Data Index: 8463363 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8681. Min Act: -0.1700
Data Index: 2647218 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8681. Min Act: -0.1700
Data Index: 1298978 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8681. Min Act: -0.1700
Data Index: 3520513 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8522. Min Act: -0.1700
Data Index: 4131137 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8522. Min Act: -0.1700
Data Index: 8575543 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8522. Min Act: -0.1700
Data Index: 4509651 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8363. Min Act: -0.1700
Data Index: 1824498 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8363. Min Act: -0.1700
Data Index: 2505047 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8363. Min Act: -0.1700
Data Index: 4509646 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8363. Min Act: -0.1700
Data Index: 8385528 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8363. Min Act: -0.1700
Data Index: 6011429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8363. Min Act: -0.1700
Data Index: 2590571 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8363. Min Act: -0.1700
Data Index: 2590572 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8363. Min Act: -0.1700
Data Index: 5598943 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8522. Min Act: -0.1700
Data Index: 5444635 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8363. Min Act: -0.1700
Data Index: 2513913 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8363. Min Act: -0.1700
Data Index: 5039619 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8998. Min Range: -2.8998
Max Act: 2.8522. Min Act: -0.1700
Data Index: 2934052 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19