Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.8934. Min Act: -0.1700
Data Index: 5387035 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.8309. Min Act: -0.1700
Data Index: 3623334 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.7684. Min Act: -0.1700
Data Index: 8214428 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.7059. Min Act: -0.1700
Data Index: 123605 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.5184. Min Act: -0.1700
Data Index: 334590 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.4559. Min Act: -0.1700
Data Index: 5032789 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.4559. Min Act: -0.1700
Data Index: 5101224 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.3934. Min Act: -0.1700
Data Index: 8411284 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.3934. Min Act: -0.1700
Data Index: 5705329 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.3934. Min Act: -0.1700
Data Index: 5874667 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.3934. Min Act: -0.1700
Data Index: 1978651 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.3309. Min Act: -0.1700
Data Index: 1343317 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.2684. Min Act: -0.1700
Data Index: 1691790 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.3309. Min Act: -0.1700
Data Index: 6205359 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.3934. Min Act: -0.1700
Data Index: 6277959 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.3309. Min Act: -0.1700
Data Index: 5998153 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.2684. Min Act: -0.1700
Data Index: 6119351 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.2684. Min Act: -0.1700
Data Index: 6853682 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.2684. Min Act: -0.1700
Data Index: 7264411 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8934. Min Range: -9.8934
Max Act: 9.2684. Min Act: -0.1700
Data Index: 5018360 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19