Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1887 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.9717. Min Act: -0.1700
Data Index: 7641633 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.9559. Min Act: -0.1700
Data Index: 2556163 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.8925. Min Act: -0.1700
Data Index: 192777 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.8925. Min Act: -0.1700
Data Index: 4528575 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.8131. Min Act: -0.1700
Data Index: 7443118 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.8290. Min Act: -0.1700
Data Index: 2689474 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7972. Min Act: -0.1700
Data Index: 6366059 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7972. Min Act: -0.1700
Data Index: 2311765 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7812. Min Act: -0.1700
Data Index: 3099369 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7653. Min Act: -0.1700
Data Index: 138662 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7653. Min Act: -0.1700
Data Index: 7659766 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7812. Min Act: -0.1700
Data Index: 4543051 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7653. Min Act: -0.1700
Data Index: 474198 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7653. Min Act: -0.1700
Data Index: 6753470 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7493. Min Act: -0.1700
Data Index: 1609413 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7653. Min Act: -0.1700
Data Index: 8699118 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7493. Min Act: -0.1700
Data Index: 2761400 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7334. Min Act: -0.1700
Data Index: 5519007 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7493. Min Act: -0.1700
Data Index: 1302666 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9717. Min Range: -2.9717
Max Act: 2.7493. Min Act: -0.1700
Data Index: 5615874 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19