Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.8960. Min Act: -0.1700
Data Index: 1244061 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.8335. Min Act: -0.1700
Data Index: 5178213 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.7085. Min Act: -0.1700
Data Index: 457970 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.6460. Min Act: -0.1700
Data Index: 8137360 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.5835. Min Act: -0.1700
Data Index: 3307849 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.5210. Min Act: -0.1700
Data Index: 3982957 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.5210. Min Act: -0.1700
Data Index: 410098 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.4585. Min Act: -0.1700
Data Index: 1902060 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.4585. Min Act: -0.1700
Data Index: 476536 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.3960. Min Act: -0.1700
Data Index: 1483369 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.3335. Min Act: -0.1700
Data Index: 4685300 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.2710. Min Act: -0.1700
Data Index: 6720718 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.2710. Min Act: -0.1700
Data Index: 3437057 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.1460. Min Act: -0.1700
Data Index: 3374359 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.0835. Min Act: -0.1700
Data Index: 1702157 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.0210. Min Act: -0.1700
Data Index: 6834530 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.0210. Min Act: -0.1700
Data Index: 8087925 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.0210. Min Act: -0.1700
Data Index: 8133362 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.0210. Min Act: -0.1700
Data Index: 5849098 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8960. Min Range: -9.8960
Max Act: 9.0210. Min Act: -0.1700
Data Index: 8679752 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19