Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1623 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.5472. Min Act: -0.1700
Data Index: 2224230 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.5149. Min Act: -0.1700
Data Index: 1045232 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.4825. Min Act: -0.1700
Data Index: 606852 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3848. Min Act: -0.1699
Data Index: 6558458 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3848. Min Act: -0.1700
Data Index: 1709835 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3521. Min Act: -0.1694
Data Index: 7152285 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3848. Min Act: -0.1700
Data Index: 637429 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3521. Min Act: -0.1700
Data Index: 55996 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3521. Min Act: -0.1700
Data Index: 2491224 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3357. Min Act: -0.1700
Data Index: 4709877 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3357. Min Act: -0.1696
Data Index: 2424462 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3521. Min Act: -0.1700
Data Index: 6235885 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3193. Min Act: -0.1700
Data Index: 1471550 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3029. Min Act: -0.1700
Data Index: 6587086 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3193. Min Act: -0.1700
Data Index: 7136400 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.2864. Min Act: -0.1696
Data Index: 8272298 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3029. Min Act: -0.1700
Data Index: 8540029 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3029. Min Act: -0.1700
Data Index: 8406047 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.3029. Min Act: -0.1700
Data Index: 1615688 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5472. Min Range: -2.5472
Max Act: 2.2864. Min Act: -0.1700
Data Index: 2192215 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19