Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5512 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.5112. Min Act: -0.1700
Data Index: 3561607 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.4487. Min Act: -0.1700
Data Index: 1043439 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.3862. Min Act: -0.1700
Data Index: 5987252 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.2612. Min Act: -0.1700
Data Index: 4490473 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.1987. Min Act: -0.1700
Data Index: 3983291 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.1987. Min Act: -0.1700
Data Index: 5987251 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.1675. Min Act: -0.1700
Data Index: 2553362 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.1050. Min Act: -0.1700
Data Index: 6026873 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.0737. Min Act: -0.1700
Data Index: 2541002 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.0737. Min Act: -0.1700
Data Index: 1201477 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.0737. Min Act: -0.1700
Data Index: 2758904 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.0737. Min Act: -0.1700
Data Index: 953012 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.0112. Min Act: -0.1700
Data Index: 725333 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.0112. Min Act: -0.1700
Data Index: 5144061 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.0112. Min Act: -0.1700
Data Index: 2382445 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5112. Min Range: -7.5112
Max Act: 7.0112. Min Act: -0.1700
Data Index: 7743910 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5112. Min Range: -7.5112
Max Act: 6.9800. Min Act: -0.1700
Data Index: 8401406 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5112. Min Range: -7.5112
Max Act: 6.9800. Min Act: -0.1700
Data Index: 2179051 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5112. Min Range: -7.5112
Max Act: 6.9800. Min Act: -0.1700
Data Index: 414989 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5112. Min Range: -7.5112
Max Act: 6.9487. Min Act: -0.1700
Data Index: 1099257 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19