Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1118 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.7574. Min Act: -0.1700
Data Index: 7044816 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.7261. Min Act: -0.1700
Data Index: 2739830 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.7261. Min Act: -0.1700
Data Index: 3701128 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6949. Min Act: -0.1700
Data Index: 2739836 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6949. Min Act: -0.1700
Data Index: 2739831 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6636. Min Act: -0.1700
Data Index: 881650 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6636. Min Act: -0.1700
Data Index: 8260952 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6324. Min Act: -0.1700
Data Index: 6825300 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6324. Min Act: -0.1700
Data Index: 6825298 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6324. Min Act: -0.1700
Data Index: 2488582 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6324. Min Act: -0.1700
Data Index: 2313549 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6011. Min Act: -0.1700
Data Index: 4566627 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6011. Min Act: -0.1700
Data Index: 4403880 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6011. Min Act: -0.1700
Data Index: 3425650 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6011. Min Act: -0.1700
Data Index: 3370347 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6324. Min Act: -0.1700
Data Index: 7420024 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6011. Min Act: -0.1700
Data Index: 2410007 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6011. Min Act: -0.1700
Data Index: 6361132 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.5699. Min Act: -0.1700
Data Index: 5150536 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7574. Min Range: -4.7574
Max Act: 4.6011. Min Act: -0.1700
Data Index: 2745052 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19