Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3755 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3995. Min Range: -6.3995
Max Act: 6.3995. Min Act: -0.1700
Data Index: 8568408 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3995. Min Range: -6.3995
Max Act: 6.2120. Min Act: -0.1700
Data Index: 4778213 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3995. Min Range: -6.3995
Max Act: 6.0245. Min Act: -0.1700
Data Index: 7210652 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3995. Min Range: -6.3995
Max Act: 6.0245. Min Act: -0.1700
Data Index: 721636 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.9308. Min Act: -0.1700
Data Index: 1619412 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.9308. Min Act: -0.1700
Data Index: 1955462 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.8995. Min Act: -0.1700
Data Index: 3212064 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.8370. Min Act: -0.1700
Data Index: 5166504 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.8370. Min Act: -0.1700
Data Index: 7515746 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.8058. Min Act: -0.1700
Data Index: 3520888 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.8058. Min Act: -0.1700
Data Index: 5782831 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.8058. Min Act: -0.1700
Data Index: 5346274 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.8058. Min Act: -0.1700
Data Index: 1252253 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.7745. Min Act: -0.1700
Data Index: 2238298 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.7745. Min Act: -0.1700
Data Index: 1168197 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.7745. Min Act: -0.1700
Data Index: 6891960 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.7433. Min Act: -0.1700
Data Index: 2287350 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.7433. Min Act: -0.1700
Data Index: 6172530 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.7745. Min Act: -0.1700
Data Index: 2306774 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3995. Min Range: -6.3995
Max Act: 5.7120. Min Act: -0.1700
Data Index: 6218331 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19