Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5346 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.8232. Min Act: -0.1700
Data Index: 8805965 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.7607. Min Act: -0.1700
Data Index: 8629549 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.7920. Min Act: -0.1700
Data Index: 7911002 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.7607. Min Act: -0.1700
Data Index: 1781244 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.7295. Min Act: -0.1700
Data Index: 2774996 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.7295. Min Act: -0.1700
Data Index: 7910997 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.6982. Min Act: -0.1700
Data Index: 3960754 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.6982. Min Act: -0.1700
Data Index: 8221625 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.6982. Min Act: -0.1700
Data Index: 5151910 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.6670. Min Act: -0.1700
Data Index: 633974 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.6357. Min Act: -0.1700
Data Index: 6632453 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.6357. Min Act: -0.1700
Data Index: 8805961 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.6357. Min Act: -0.1700
Data Index: 4125613 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.6357. Min Act: -0.1700
Data Index: 7145823 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.6357. Min Act: -0.1700
Data Index: 5151917 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.6045. Min Act: -0.1700
Data Index: 3645353 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.6045. Min Act: -0.1700
Data Index: 1854359 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.6045. Min Act: -0.1700
Data Index: 2738210 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.5732. Min Act: -0.1700
Data Index: 3369560 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8232. Min Range: -4.8232
Max Act: 4.5732. Min Act: -0.1700
Data Index: 7910999 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19