Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2465 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0717. Min Range: -7.0717
Max Act: 7.0717. Min Act: -0.1700
Data Index: 63593 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.9467. Min Act: -0.1700
Data Index: 3269568 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.9154. Min Act: -0.1700
Data Index: 7338509 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.9154. Min Act: -0.1700
Data Index: 6377167 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.8842. Min Act: -0.1700
Data Index: 2057437 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.8529. Min Act: -0.1700
Data Index: 5492776 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.8529. Min Act: -0.1700
Data Index: 5705146 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.7904. Min Act: -0.1700
Data Index: 7247375 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.7592. Min Act: -0.1700
Data Index: 5038306 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.7592. Min Act: -0.1700
Data Index: 1318773 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.7592. Min Act: -0.1700
Data Index: 7908772 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.7592. Min Act: -0.1700
Data Index: 8784193 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.7592. Min Act: -0.1700
Data Index: 7918316 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6967. Min Act: -0.1700
Data Index: 7230488 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.7279. Min Act: -0.1700
Data Index: 2781161 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6967. Min Act: -0.1700
Data Index: 5787341 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6967. Min Act: -0.1700
Data Index: 7895772 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6967. Min Act: -0.1700
Data Index: 6746974 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6654. Min Act: -0.1700
Data Index: 1784525 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6654. Min Act: -0.1700
Data Index: 8474217 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19