Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1578. Min Range: -7.1578
Max Act: 7.1578. Min Act: -0.1700
Data Index: 1260788 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.7203. Min Act: -0.1700
Data Index: 7767828 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.6891. Min Act: -0.1700
Data Index: 5078624 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.6578. Min Act: -0.1700
Data Index: 1530101 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.6578. Min Act: -0.1700
Data Index: 4699079 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.6266. Min Act: -0.1700
Data Index: 5185005 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.6578. Min Act: -0.1700
Data Index: 1766478 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.5641. Min Act: -0.1700
Data Index: 3547943 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.5328. Min Act: -0.1700
Data Index: 4460238 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.5016. Min Act: -0.1700
Data Index: 1019740 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.3766. Min Act: -0.1700
Data Index: 4285363 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.3766. Min Act: -0.1700
Data Index: 4460239 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.4078. Min Act: -0.1700
Data Index: 5476693 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.3141. Min Act: -0.1700
Data Index: 2340372 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.3766. Min Act: -0.1700
Data Index: 2992133 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.2828. Min Act: -0.1700
Data Index: 392106 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.2828. Min Act: -0.1700
Data Index: 5107888 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.2203. Min Act: -0.1700
Data Index: 6461248 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.3141. Min Act: -0.1700
Data Index: 5132639 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1578. Min Range: -7.1578
Max Act: 6.2828. Min Act: -0.1700
Data Index: 1631765 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19