Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6300 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.3983. Min Act: -0.1700
Data Index: 3758077 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.2733. Min Act: -0.1700
Data Index: 5556432 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.2733. Min Act: -0.1700
Data Index: 467061 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.2733. Min Act: -0.1700
Data Index: 5508736 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.1795. Min Act: -0.1700
Data Index: 3529826 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.1483. Min Act: -0.1700
Data Index: 2626367 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.1795. Min Act: -0.1700
Data Index: 355166 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.1170. Min Act: -0.1700
Data Index: 4622389 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.1170. Min Act: -0.1700
Data Index: 7707114 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.1170. Min Act: -0.1700
Data Index: 3788665 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.1170. Min Act: -0.1700
Data Index: 2574256 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.0858. Min Act: -0.1700
Data Index: 4417226 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.0858. Min Act: -0.1700
Data Index: 4543120 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.0858. Min Act: -0.1700
Data Index: 8258445 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.0858. Min Act: -0.1700
Data Index: 4859035 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.0545. Min Act: -0.1700
Data Index: 5126716 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.0545. Min Act: -0.1700
Data Index: 2940704 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3983. Min Range: -5.3983
Max Act: 5.0858. Min Act: -0.1700
Data Index: 1344652 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3983. Min Range: -5.3983
Max Act: 4.9920. Min Act: -0.1700
Data Index: 556610 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3983. Min Range: -5.3983
Max Act: 4.9920. Min Act: -0.1700
Data Index: 1596924 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19