Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3530 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.4124. Min Act: -0.1700
Data Index: 1208388 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.3187. Min Act: -0.1700
Data Index: 2241831 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.2249. Min Act: -0.1700
Data Index: 6826002 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.2249. Min Act: -0.1700
Data Index: 6514060 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.2249. Min Act: -0.1700
Data Index: 6017757 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.2562. Min Act: -0.1700
Data Index: 656224 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.1937. Min Act: -0.1700
Data Index: 4694647 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.1312. Min Act: -0.1700
Data Index: 7621993 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.1937. Min Act: -0.1700
Data Index: 554182 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.1312. Min Act: -0.1700
Data Index: 6579117 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.1312. Min Act: -0.1700
Data Index: 4076425 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.1312. Min Act: -0.1700
Data Index: 1299588 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.1312. Min Act: -0.1700
Data Index: 8198587 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.0999. Min Act: -0.1700
Data Index: 280317 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.0687. Min Act: -0.1700
Data Index: 6461381 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.0374. Min Act: -0.1700
Data Index: 5294548 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.0062. Min Act: -0.1700
Data Index: 7548336 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4124. Min Range: -5.4124
Max Act: 5.0062. Min Act: -0.1700
Data Index: 2057071 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4124. Min Range: -5.4124
Max Act: 4.9749. Min Act: -0.1700
Data Index: 7155679 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4124. Min Range: -5.4124
Max Act: 4.9749. Min Act: -0.1700
Data Index: 6216673 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19