Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1508 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2682. Min Range: -4.2682
Max Act: 4.2682. Min Act: -0.1700
Data Index: 7433188 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2682. Min Range: -4.2682
Max Act: 4.2370. Min Act: -0.1700
Data Index: 368035 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2682. Min Range: -4.2682
Max Act: 4.2370. Min Act: -0.1700
Data Index: 570263 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2682. Min Range: -4.2682
Max Act: 4.1432. Min Act: -0.1700
Data Index: 7964659 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2682. Min Range: -4.2682
Max Act: 4.1119. Min Act: -0.1700
Data Index: 2401755 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2682. Min Range: -4.2682
Max Act: 4.1119. Min Act: -0.1700
Data Index: 7435702 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2682. Min Range: -4.2682
Max Act: 4.1119. Min Act: -0.1700
Data Index: 2637172 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2682. Min Range: -4.2682
Max Act: 4.0494. Min Act: -0.1700
Data Index: 570262 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2682. Min Range: -4.2682
Max Act: 4.0182. Min Act: -0.1700
Data Index: 4343384 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2682. Min Range: -4.2682
Max Act: 4.0182. Min Act: -0.1700
Data Index: 1643741 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2682. Min Range: -4.2682
Max Act: 4.0182. Min Act: -0.1700
Data Index: 8257196 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2682. Min Range: -4.2682
Max Act: 3.9869. Min Act: -0.1700
Data Index: 1127546 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2682. Min Range: -4.2682
Max Act: 3.9869. Min Act: -0.1700
Data Index: 6617525 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2682. Min Range: -4.2682
Max Act: 3.9556. Min Act: -0.1700
Data Index: 8147053 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2682. Min Range: -4.2682
Max Act: 3.9244. Min Act: -0.1700
Data Index: 1703543 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2682. Min Range: -4.2682
Max Act: 3.9244. Min Act: -0.1700
Data Index: 4087628 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2682. Min Range: -4.2682
Max Act: 3.9087. Min Act: -0.1700
Data Index: 2774643 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2682. Min Range: -4.2682
Max Act: 3.8775. Min Act: -0.1700
Data Index: 507480 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2682. Min Range: -4.2682
Max Act: 3.8931. Min Act: -0.1700
Data Index: 8017921 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2682. Min Range: -4.2682
Max Act: 3.8931. Min Act: -0.1700
Data Index: 6027326 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19