Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3162 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0088. Min Range: -8.0088
Max Act: 8.0088. Min Act: -0.1700
Data Index: 5069187 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0088. Min Range: -8.0088
Max Act: 7.3838. Min Act: -0.1700
Data Index: 2933440 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0088. Min Range: -8.0088
Max Act: 7.3838. Min Act: -0.1700
Data Index: 8366190 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0088. Min Range: -8.0088
Max Act: 7.3213. Min Act: -0.1700
Data Index: 7516297 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0088. Min Range: -8.0088
Max Act: 7.1651. Min Act: -0.1700
Data Index: 5069188 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0088. Min Range: -8.0088
Max Act: 7.1026. Min Act: -0.1700
Data Index: 4943315 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0088. Min Range: -8.0088
Max Act: 7.0401. Min Act: -0.1700
Data Index: 6780885 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0088. Min Range: -8.0088
Max Act: 7.0713. Min Act: -0.1700
Data Index: 7986063 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0088. Min Range: -8.0088
Max Act: 7.0088. Min Act: -0.1700
Data Index: 1818982 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0088. Min Range: -8.0088
Max Act: 7.0088. Min Act: -0.1700
Data Index: 1199751 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0088. Min Range: -8.0088
Max Act: 6.9776. Min Act: -0.1700
Data Index: 7837008 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0088. Min Range: -8.0088
Max Act: 6.9463. Min Act: -0.1700
Data Index: 7751491 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0088. Min Range: -8.0088
Max Act: 6.8838. Min Act: -0.1700
Data Index: 1157751 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0088. Min Range: -8.0088
Max Act: 6.8838. Min Act: -0.1700
Data Index: 3793873 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0088. Min Range: -8.0088
Max Act: 6.8838. Min Act: -0.1700
Data Index: 7103221 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0088. Min Range: -8.0088
Max Act: 6.8526. Min Act: -0.1700
Data Index: 8638022 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0088. Min Range: -8.0088
Max Act: 6.8526. Min Act: -0.1700
Data Index: 3437824 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0088. Min Range: -8.0088
Max Act: 6.8526. Min Act: -0.1700
Data Index: 1684802 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0088. Min Range: -8.0088
Max Act: 6.8213. Min Act: -0.1700
Data Index: 449058 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0088. Min Range: -8.0088
Max Act: 6.8213. Min Act: -0.1700
Data Index: 8606182 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19