Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5518 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1983. Min Range: -7.1983
Max Act: 7.1983. Min Act: -0.1700
Data Index: 3303086 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1983. Min Range: -7.1983
Max Act: 7.1671. Min Act: -0.1700
Data Index: 3925754 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1983. Min Range: -7.1983
Max Act: 7.1046. Min Act: -0.1700
Data Index: 7073148 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1983. Min Range: -7.1983
Max Act: 7.0733. Min Act: -0.1700
Data Index: 4288073 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.9796. Min Act: -0.1700
Data Index: 3820586 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.9796. Min Act: -0.1700
Data Index: 8548193 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8858. Min Act: -0.1700
Data Index: 5806679 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.9171. Min Act: -0.1700
Data Index: 5260594 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8546. Min Act: -0.1700
Data Index: 5214174 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8858. Min Act: -0.1700
Data Index: 721351 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8858. Min Act: -0.1700
Data Index: 471670 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8858. Min Act: -0.1700
Data Index: 1367811 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8858. Min Act: -0.1700
Data Index: 5038959 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8546. Min Act: -0.1700
Data Index: 3400565 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8233. Min Act: -0.1700
Data Index: 3624869 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8546. Min Act: -0.1700
Data Index: 8119866 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8546. Min Act: -0.1700
Data Index: 679132 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8233. Min Act: -0.1700
Data Index: 8179545 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8233. Min Act: -0.1700
Data Index: 4180424 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.7921. Min Act: -0.1700
Data Index: 7057224 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19