Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3798 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0067. Min Range: -2.0067
Max Act: 2.0067. Min Act: -0.1700
Data Index: 5965160 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.9729. Min Act: -0.1700
Data Index: 3271074 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.9559. Min Act: -0.1700
Data Index: 8066145 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.9390. Min Act: -0.1700
Data Index: 175540 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.9219. Min Act: -0.1700
Data Index: 832628 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.9390. Min Act: -0.1699
Data Index: 2734928 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.9049. Min Act: -0.1700
Data Index: 2176422 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.9049. Min Act: -0.1700
Data Index: 5769680 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.9049. Min Act: -0.1700
Data Index: 4967664 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.9049. Min Act: -0.1700
Data Index: 7411882 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.9049. Min Act: -0.1700
Data Index: 7916635 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.9049. Min Act: -0.1700
Data Index: 6478280 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.8879. Min Act: -0.1700
Data Index: 1647663 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.8879. Min Act: -0.1700
Data Index: 612153 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.9049. Min Act: -0.1700
Data Index: 4795105 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.8879. Min Act: -0.1700
Data Index: 2188098 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.8708. Min Act: -0.1700
Data Index: 6206870 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.8622. Min Act: -0.1700
Data Index: 4095271 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.8537. Min Act: -0.1700
Data Index: 221079 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0067. Min Range: -2.0067
Max Act: 1.8708. Min Act: -0.1700
Data Index: 7538696 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19