Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3887 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.5830. Min Act: -0.1700
Data Index: 2875966 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.5830. Min Act: -0.1700
Data Index: 7025486 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.5830. Min Act: -0.1699
Data Index: 8764203 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.5518. Min Act: -0.1700
Data Index: 6674230 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.5205. Min Act: -0.1700
Data Index: 958239 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.5518. Min Act: -0.1700
Data Index: 1157510 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.5518. Min Act: -0.1700
Data Index: 3184673 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.5518. Min Act: -0.1695
Data Index: 3872125 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.5205. Min Act: -0.1700
Data Index: 7244818 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.5205. Min Act: -0.1700
Data Index: 753190 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.5205. Min Act: -0.1700
Data Index: 1802511 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.5205. Min Act: -0.1700
Data Index: 5269526 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.4893. Min Act: -0.1694
Data Index: 2046794 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.4893. Min Act: -0.1700
Data Index: 466337 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.4893. Min Act: -0.1694
Data Index: 4949257 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.4893. Min Act: -0.1700
Data Index: 4842052 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.4893. Min Act: -0.1700
Data Index: 8210011 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.4893. Min Act: -0.1700
Data Index: 7279770 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.4893. Min Act: -0.1700
Data Index: 5475501 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5830. Min Range: -6.5830
Max Act: 6.4580. Min Act: -0.1700
Data Index: 1808309 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19