Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1174 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1614. Min Range: -5.1614
Max Act: 5.1614. Min Act: -0.1700
Data Index: 31617 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1614. Min Range: -5.1614
Max Act: 5.1302. Min Act: -0.1700
Data Index: 6207726 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1614. Min Range: -5.1614
Max Act: 5.0364. Min Act: -0.1700
Data Index: 6538060 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1614. Min Range: -5.1614
Max Act: 5.0364. Min Act: -0.1700
Data Index: 3647590 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.9739. Min Act: -0.1700
Data Index: 5664039 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.9114. Min Act: -0.1700
Data Index: 4181749 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.8802. Min Act: -0.1700
Data Index: 8745467 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.8802. Min Act: -0.1700
Data Index: 3945495 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.8489. Min Act: -0.1700
Data Index: 233990 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.8489. Min Act: -0.1700
Data Index: 3873975 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.8489. Min Act: -0.1700
Data Index: 2227132 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.8489. Min Act: -0.1700
Data Index: 3256539 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.8177. Min Act: -0.1700
Data Index: 3400516 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.8177. Min Act: -0.1700
Data Index: 4475594 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.8489. Min Act: -0.1700
Data Index: 6241542 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.7552. Min Act: -0.1700
Data Index: 1383190 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.7864. Min Act: -0.1700
Data Index: 617243 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.7864. Min Act: -0.1700
Data Index: 4873231 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.7864. Min Act: -0.1700
Data Index: 3668030 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1614. Min Range: -5.1614
Max Act: 4.7864. Min Act: -0.1700
Data Index: 4878134 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19