Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1693 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0687. Min Act: -0.1700
Data Index: 5096164 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0518. Min Act: -0.1700
Data Index: 4893382 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0518. Min Act: -0.1700
Data Index: 4325128 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0182. Min Act: -0.1700
Data Index: 4150791 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0013. Min Act: -0.1699
Data Index: 3264227 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0350. Min Act: -0.1700
Data Index: 5697807 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9844. Min Act: -0.1700
Data Index: 7279646 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9844. Min Act: -0.1700
Data Index: 6918118 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9844. Min Act: -0.1700
Data Index: 5845590 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9844. Min Act: -0.1700
Data Index: 5061979 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9674. Min Act: -0.1700
Data Index: 7589294 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9674. Min Act: -0.1700
Data Index: 4548892 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9674. Min Act: -0.1700
Data Index: 4353471 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9674. Min Act: -0.1700
Data Index: 1999370 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9674. Min Act: -0.1700
Data Index: 492712 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9674. Min Act: -0.1700
Data Index: 3741749 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9674. Min Act: -0.1699
Data Index: 2562473 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9674. Min Act: -0.1700
Data Index: 3394776 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9505. Min Act: -0.1700
Data Index: 4796708 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9844. Min Act: -0.1700
Data Index: 4628160 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19