Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 562 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.5210. Min Act: -0.1700
Data Index: 6082888 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.4740. Min Act: -0.1700
Data Index: 780041 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.4113. Min Act: -0.1700
Data Index: 5210480 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.3643. Min Act: -0.1700
Data Index: 5872278 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.3329. Min Act: -0.1700
Data Index: 4619563 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.3172. Min Act: -0.1700
Data Index: 8301477 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.3329. Min Act: -0.1700
Data Index: 6462111 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.3172. Min Act: -0.1700
Data Index: 3034894 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.3172. Min Act: -0.1700
Data Index: 1923101 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.3172. Min Act: -0.1700
Data Index: 1933025 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.3015. Min Act: -0.1700
Data Index: 1628785 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.2701. Min Act: -0.1700
Data Index: 1933026 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.2544. Min Act: -0.1700
Data Index: 5622181 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.2544. Min Act: -0.1700
Data Index: 3868406 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.2544. Min Act: -0.1700
Data Index: 4044428 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.2387. Min Act: -0.1700
Data Index: 2498510 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.2073. Min Act: -0.1700
Data Index: 5563203 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.2230. Min Act: -0.1700
Data Index: 3632255 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.2387. Min Act: -0.1700
Data Index: 7039221 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5210. Min Range: -3.5210
Max Act: 3.2230. Min Act: -0.1700
Data Index: 4070272 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19