Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 250 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2294. Min Range: -6.2294
Max Act: 6.2294. Min Act: -0.1700
Data Index: 553860 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2294. Min Range: -6.2294
Max Act: 6.2294. Min Act: -0.1700
Data Index: 1137090 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.9169. Min Act: -0.1700
Data Index: 4514899 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.9169. Min Act: -0.1700
Data Index: 1843013 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.7919. Min Act: -0.1700
Data Index: 8745650 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.7607. Min Act: -0.1700
Data Index: 5920690 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.7607. Min Act: -0.1700
Data Index: 7881391 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.7607. Min Act: -0.1700
Data Index: 3015912 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.7607. Min Act: -0.1700
Data Index: 7244275 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6982. Min Act: -0.1700
Data Index: 2350439 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6982. Min Act: -0.1700
Data Index: 7749450 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6669. Min Act: -0.1700
Data Index: 8326204 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6357. Min Act: -0.1700
Data Index: 1808035 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6357. Min Act: -0.1700
Data Index: 3550022 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6357. Min Act: -0.1700
Data Index: 59264 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6044. Min Act: -0.1700
Data Index: 3683941 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6044. Min Act: -0.1700
Data Index: 2313260 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6044. Min Act: -0.1700
Data Index: 7204471 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6044. Min Act: -0.1700
Data Index: 3782211 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.5732. Min Act: -0.1700
Data Index: 1070268 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19