Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1426 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.6701. Min Act: -0.1700
Data Index: 777102 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.5451. Min Act: -0.1700
Data Index: 2633661 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.5451. Min Act: -0.1700
Data Index: 3577531 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.5451. Min Act: -0.1700
Data Index: 1243018 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.4826. Min Act: -0.1700
Data Index: 3881769 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.4826. Min Act: -0.1700
Data Index: 7476805 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.4514. Min Act: -0.1700
Data Index: 5858845 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.4826. Min Act: -0.1700
Data Index: 7910260 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.4201. Min Act: -0.1700
Data Index: 3549730 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.4201. Min Act: -0.1700
Data Index: 2870684 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.3576. Min Act: -0.1700
Data Index: 3750937 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.3576. Min Act: -0.1700
Data Index: 4077875 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.3889. Min Act: -0.1700
Data Index: 7713116 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.3889. Min Act: -0.1700
Data Index: 5077496 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.3576. Min Act: -0.1700
Data Index: 4791842 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.3264. Min Act: -0.1700
Data Index: 357465 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.3576. Min Act: -0.1700
Data Index: 4315177 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.3576. Min Act: -0.1700
Data Index: 4155132 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.3576. Min Act: -0.1700
Data Index: 1032004 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6701. Min Range: -6.6701
Max Act: 6.3264. Min Act: -0.1700
Data Index: 4487624 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19