Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1212 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.4683. Min Act: -0.1700
Data Index: 4618366 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.3745. Min Act: -0.1700
Data Index: 4426696 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.3120. Min Act: -0.1700
Data Index: 2020266 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.2808. Min Act: -0.1700
Data Index: 6201394 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.2495. Min Act: -0.1700
Data Index: 3797435 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.2183. Min Act: -0.1700
Data Index: 6542600 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.2183. Min Act: -0.1700
Data Index: 5011866 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.2183. Min Act: -0.1700
Data Index: 6287377 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.2183. Min Act: -0.1700
Data Index: 2020270 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.1558. Min Act: -0.1700
Data Index: 22016 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.1870. Min Act: -0.1700
Data Index: 26767 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.1870. Min Act: -0.1700
Data Index: 5112714 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.1558. Min Act: -0.1700
Data Index: 26768 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.1245. Min Act: -0.1700
Data Index: 3221403 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.1245. Min Act: -0.1700
Data Index: 7861162 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.0933. Min Act: -0.1700
Data Index: 7320889 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.0933. Min Act: -0.1700
Data Index: 8381176 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.0620. Min Act: -0.1700
Data Index: 2915044 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.0933. Min Act: -0.1700
Data Index: 7285169 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4683. Min Range: -7.4683
Max Act: 7.0933. Min Act: -0.1700
Data Index: 1900774 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19