Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4529 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3161. Min Range: -6.3161
Max Act: 6.3161. Min Act: -0.1700
Data Index: 4140255 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3161. Min Range: -6.3161
Max Act: 6.1911. Min Act: -0.1700
Data Index: 2462330 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3161. Min Range: -6.3161
Max Act: 6.1599. Min Act: -0.1700
Data Index: 3888633 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3161. Min Range: -6.3161
Max Act: 6.1599. Min Act: -0.1700
Data Index: 6229413 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3161. Min Range: -6.3161
Max Act: 6.0661. Min Act: -0.1700
Data Index: 2351176 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3161. Min Range: -6.3161
Max Act: 6.0036. Min Act: -0.1700
Data Index: 2270240 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3161. Min Range: -6.3161
Max Act: 6.0036. Min Act: -0.1700
Data Index: 6144383 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3161. Min Range: -6.3161
Max Act: 6.0036. Min Act: -0.1700
Data Index: 4140256 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3161. Min Range: -6.3161
Max Act: 5.9724. Min Act: -0.1700
Data Index: 8261248 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3161. Min Range: -6.3161
Max Act: 5.9724. Min Act: -0.1700
Data Index: 1479152 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3161. Min Range: -6.3161
Max Act: 5.9411. Min Act: -0.1700
Data Index: 6371324 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3161. Min Range: -6.3161
Max Act: 5.9411. Min Act: -0.1700
Data Index: 4221873 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3161. Min Range: -6.3161
Max Act: 5.9411. Min Act: -0.1700
Data Index: 1661748 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3161. Min Range: -6.3161
Max Act: 5.9099. Min Act: -0.1700
Data Index: 3573785 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3161. Min Range: -6.3161
Max Act: 5.9099. Min Act: -0.1700
Data Index: 5324146 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3161. Min Range: -6.3161
Max Act: 5.8786. Min Act: -0.1700
Data Index: 6861646 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3161. Min Range: -6.3161
Max Act: 5.8786. Min Act: -0.1700
Data Index: 5301218 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3161. Min Range: -6.3161
Max Act: 5.8786. Min Act: -0.1700
Data Index: 5928898 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3161. Min Range: -6.3161
Max Act: 5.8786. Min Act: -0.1700
Data Index: 5326250 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3161. Min Range: -6.3161
Max Act: 5.8786. Min Act: -0.1700
Data Index: 115041 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19