Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.3100. Min Act: -0.1700
Data Index: 5491523 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.2162. Min Act: -0.1700
Data Index: 1332873 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.1850. Min Act: -0.1700
Data Index: 3596819 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.1537. Min Act: -0.1700
Data Index: 5142388 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.1225. Min Act: -0.1700
Data Index: 650183 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.1225. Min Act: -0.1700
Data Index: 6286693 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.0600. Min Act: -0.1700
Data Index: 2715525 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.0912. Min Act: -0.1700
Data Index: 8287213 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.1225. Min Act: -0.1700
Data Index: 2085530 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.0600. Min Act: -0.1700
Data Index: 1395410 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.1225. Min Act: -0.1700
Data Index: 496152 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.1225. Min Act: -0.1700
Data Index: 7452003 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.0600. Min Act: -0.1700
Data Index: 6135677 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.0600. Min Act: -0.1700
Data Index: 5349231 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.0912. Min Act: -0.1699
Data Index: 2060682 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.0600. Min Act: -0.1700
Data Index: 4777026 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.0912. Min Act: -0.1700
Data Index: 1714369 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.0600. Min Act: -0.1700
Data Index: 1077162 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.0600. Min Act: -0.1700
Data Index: 2290988 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3100. Min Range: -5.3100
Max Act: 5.0600. Min Act: -0.1700
Data Index: 7010265 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19