Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.4134. Min Act: -0.1700
Data Index: 256526 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.3196. Min Act: -0.1700
Data Index: 2998671 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.2884. Min Act: -0.1700
Data Index: 7913455 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.2259. Min Act: -0.1700
Data Index: 8586598 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.1634. Min Act: -0.1700
Data Index: 4647207 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.1009. Min Act: -0.1700
Data Index: 2657489 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.0071. Min Act: -0.1700
Data Index: 7913453 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.0071. Min Act: -0.1700
Data Index: 47271 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.9759. Min Act: -0.1700
Data Index: 1424898 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.9759. Min Act: -0.1700
Data Index: 8586601 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.9134. Min Act: -0.1700
Data Index: 7913603 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.9759. Min Act: -0.1700
Data Index: 588223 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.8821. Min Act: -0.1700
Data Index: 7900690 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.8509. Min Act: -0.1700
Data Index: 4325656 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.9134. Min Act: -0.1700
Data Index: 11934 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.8509. Min Act: -0.1700
Data Index: 8174488 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.8509. Min Act: -0.1700
Data Index: 7379780 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.8821. Min Act: -0.1700
Data Index: 7093679 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.8509. Min Act: -0.1700
Data Index: 2504459 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.8509. Min Act: -0.1700
Data Index: 7093680 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19