Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3612 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0811. Min Range: -4.0811
Max Act: 4.0811. Min Act: -0.1700
Data Index: 7102694 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0811. Min Range: -4.0811
Max Act: 4.0811. Min Act: -0.1700
Data Index: 5849835 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.8310. Min Act: -0.1700
Data Index: 5519581 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7684. Min Act: -0.1700
Data Index: 6169835 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7997. Min Act: -0.1700
Data Index: 2318867 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7997. Min Act: -0.1700
Data Index: 38836 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7684. Min Act: -0.1700
Data Index: 3655341 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7997. Min Act: -0.1700
Data Index: 8346379 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7684. Min Act: -0.1700
Data Index: 5793959 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7684. Min Act: -0.1700
Data Index: 5911319 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7684. Min Act: -0.1700
Data Index: 2597042 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7684. Min Act: -0.1700
Data Index: 4260909 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7684. Min Act: -0.1700
Data Index: 7795482 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7684. Min Act: -0.1700
Data Index: 163368 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7372. Min Act: -0.1700
Data Index: 4950945 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7372. Min Act: -0.1700
Data Index: 1219099 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7372. Min Act: -0.1700
Data Index: 3502320 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7372. Min Act: -0.1700
Data Index: 6926157 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7059. Min Act: -0.1700
Data Index: 5074122 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.6746. Min Act: -0.1700
Data Index: 5265139 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19