Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 197 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.6872. Min Act: -0.1700
Data Index: 6615443 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.6712. Min Act: -0.1700
Data Index: 2102630 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.6712. Min Act: -0.1700
Data Index: 2957742 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.6551. Min Act: -0.1700
Data Index: 5545590 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.6391. Min Act: -0.1700
Data Index: 2364191 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.6391. Min Act: -0.1700
Data Index: 1383053 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.6230. Min Act: -0.1700
Data Index: 245634 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.5908. Min Act: -0.1700
Data Index: 8268871 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.5908. Min Act: -0.1700
Data Index: 4476161 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.5747. Min Act: -0.1700
Data Index: 5622014 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.5424. Min Act: -0.1700
Data Index: 495867 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.5424. Min Act: -0.1700
Data Index: 7762253 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.5424. Min Act: -0.1700
Data Index: 4657857 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.5101. Min Act: -0.1700
Data Index: 7593196 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.5263. Min Act: -0.1700
Data Index: 7988805 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.4939. Min Act: -0.1700
Data Index: 7330630 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.5101. Min Act: -0.1700
Data Index: 4419746 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.5101. Min Act: -0.1700
Data Index: 3957760 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.5101. Min Act: -0.1700
Data Index: 5399786 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6872. Min Range: -2.6872
Max Act: 2.4939. Min Act: -0.1700
Data Index: 5122838 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19