Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1173 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.5130. Min Act: -0.1700
Data Index: 1965906 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.4192. Min Act: -0.1700
Data Index: 7020579 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2317. Min Act: -0.1700
Data Index: 3910189 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1692. Min Act: -0.1700
Data Index: 3690920 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1067. Min Act: -0.1700
Data Index: 4568746 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1692. Min Act: -0.1700
Data Index: 5721048 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1067. Min Act: -0.1700
Data Index: 4868174 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1067. Min Act: -0.1700
Data Index: 358481 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.0755. Min Act: -0.1700
Data Index: 5721047 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.0755. Min Act: -0.1700
Data Index: 3236639 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.0442. Min Act: -0.1700
Data Index: 4881508 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.0442. Min Act: -0.1700
Data Index: 3485318 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.0130. Min Act: -0.1700
Data Index: 6197622 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5130. Min Range: -5.5130
Max Act: 4.9817. Min Act: -0.1700
Data Index: 8168530 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.0130. Min Act: -0.1700
Data Index: 2410550 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5130. Min Range: -5.5130
Max Act: 4.9817. Min Act: -0.1700
Data Index: 7902471 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5130. Min Range: -5.5130
Max Act: 4.9817. Min Act: -0.1700
Data Index: 3335104 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5130. Min Range: -5.5130
Max Act: 4.9817. Min Act: -0.1700
Data Index: 4983901 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5130. Min Range: -5.5130
Max Act: 4.9505. Min Act: -0.1700
Data Index: 865335 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5130. Min Range: -5.5130
Max Act: 4.9505. Min Act: -0.1700
Data Index: 317192 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19