Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 335 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.5005. Min Act: -0.1700
Data Index: 7418374 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.4380. Min Act: -0.1700
Data Index: 8508958 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.4380. Min Act: -0.1700
Data Index: 5990739 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.4380. Min Act: -0.1700
Data Index: 5626993 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.3130. Min Act: -0.1700
Data Index: 6081077 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.3755. Min Act: -0.1700
Data Index: 477141 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.3130. Min Act: -0.1700
Data Index: 5307267 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.3130. Min Act: -0.1700
Data Index: 8161811 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.3130. Min Act: -0.1700
Data Index: 6340712 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.3130. Min Act: -0.1700
Data Index: 6877284 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.2505. Min Act: -0.1700
Data Index: 7953869 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.2505. Min Act: -0.1700
Data Index: 609512 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.1880. Min Act: -0.1700
Data Index: 2569169 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.2505. Min Act: -0.1700
Data Index: 7026940 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.1880. Min Act: -0.1700
Data Index: 305779 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.1880. Min Act: -0.1700
Data Index: 6461196 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.1255. Min Act: -0.1700
Data Index: 37731 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.1255. Min Act: -0.1700
Data Index: 1450466 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.1255. Min Act: -0.1700
Data Index: 5781186 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.1255. Min Act: -0.1700
Data Index: 2978430 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19