Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1327 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.8664. Min Act: -0.1700
Data Index: 548017 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.8664. Min Act: -0.1700
Data Index: 7205130 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.8493. Min Act: -0.1700
Data Index: 6217096 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.8321. Min Act: -0.1700
Data Index: 8513370 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.8321. Min Act: -0.1700
Data Index: 1521603 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.8321. Min Act: -0.1700
Data Index: 5783097 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.8236. Min Act: -0.1700
Data Index: 7759066 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.8064. Min Act: -0.1692
Data Index: 2579184 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.8236. Min Act: -0.1699
Data Index: 1317965 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.7978. Min Act: -0.1700
Data Index: 27510 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.8064. Min Act: -0.1700
Data Index: 8338401 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.7978. Min Act: -0.1700
Data Index: 6706753 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.7978. Min Act: -0.1700
Data Index: 6426059 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.7978. Min Act: -0.1700
Data Index: 914333 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.7892. Min Act: -0.1700
Data Index: 5006982 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.7978. Min Act: -0.1700
Data Index: 3788305 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.7978. Min Act: -0.1699
Data Index: 2364226 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.7978. Min Act: -0.1700
Data Index: 2864845 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.7978. Min Act: -0.1700
Data Index: 3727525 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8664. Min Range: -1.8664
Max Act: 1.7806. Min Act: -0.1700
Data Index: 7993565 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19