Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0856. Min Range: -7.0856
Max Act: 7.0856. Min Act: -0.1700
Data Index: 5356503 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.3668. Min Act: -0.1700
Data Index: 8274791 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.3668. Min Act: -0.1700
Data Index: 3695656 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.3043. Min Act: -0.1700
Data Index: 5774092 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.2106. Min Act: -0.1700
Data Index: 4001684 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.2731. Min Act: -0.1700
Data Index: 6508559 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.2106. Min Act: -0.1700
Data Index: 756781 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.2106. Min Act: -0.1700
Data Index: 5775452 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.2106. Min Act: -0.1700
Data Index: 7097937 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.2106. Min Act: -0.1700
Data Index: 8748892 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.1481. Min Act: -0.1700
Data Index: 196916 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.1793. Min Act: -0.1700
Data Index: 1055064 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.1168. Min Act: -0.1700
Data Index: 4851094 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.1168. Min Act: -0.1700
Data Index: 173943 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.0856. Min Act: -0.1700
Data Index: 8633340 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.1168. Min Act: -0.1700
Data Index: 1365667 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.1168. Min Act: -0.1700
Data Index: 5478466 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.1168. Min Act: -0.1700
Data Index: 7173352 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.1168. Min Act: -0.1700
Data Index: 1208865 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0856. Min Range: -7.0856
Max Act: 6.0856. Min Act: -0.1700
Data Index: 8505853 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19