Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5813 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0117. Min Range: -5.0117
Max Act: 5.0117. Min Act: -0.1700
Data Index: 6794100 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0117. Min Range: -5.0117
Max Act: 5.0117. Min Act: -0.1700
Data Index: 72594 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0117. Min Range: -5.0117
Max Act: 5.0117. Min Act: -0.1700
Data Index: 5779077 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0117. Min Range: -5.0117
Max Act: 5.0117. Min Act: -0.1700
Data Index: 1091776 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0117. Min Range: -5.0117
Max Act: 5.0117. Min Act: -0.1700
Data Index: 3473841 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.8867. Min Act: -0.1700
Data Index: 2136612 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.7305. Min Act: -0.1700
Data Index: 6651618 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.7305. Min Act: -0.1700
Data Index: 3294054 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.6992. Min Act: -0.1700
Data Index: 4032142 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.6992. Min Act: -0.1700
Data Index: 3353304 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.6680. Min Act: -0.1700
Data Index: 8159962 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.6680. Min Act: -0.1699
Data Index: 344924 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.6680. Min Act: -0.1700
Data Index: 4799525 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.6680. Min Act: -0.1700
Data Index: 7526198 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.6367. Min Act: -0.1700
Data Index: 6010626 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.6055. Min Act: -0.1700
Data Index: 2890769 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.6367. Min Act: -0.1700
Data Index: 6537287 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.6367. Min Act: -0.1700
Data Index: 2307300 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.6367. Min Act: -0.1700
Data Index: 2982745 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0117. Min Range: -5.0117
Max Act: 4.6055. Min Act: -0.1700
Data Index: 4938576 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19