Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5331 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5566. Min Range: -8.5566
Max Act: 8.5566. Min Act: -0.1700
Data Index: 1140029 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5566. Min Range: -8.5566
Max Act: 8.4316. Min Act: -0.1700
Data Index: 5842288 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5566. Min Range: -8.5566
Max Act: 8.3691. Min Act: -0.1700
Data Index: 3192879 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5566. Min Range: -8.5566
Max Act: 8.1816. Min Act: -0.1700
Data Index: 6490177 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5566. Min Range: -8.5566
Max Act: 8.1816. Min Act: -0.1700
Data Index: 4931615 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5566. Min Range: -8.5566
Max Act: 8.0566. Min Act: -0.1700
Data Index: 897149 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5566. Min Range: -8.5566
Max Act: 8.0566. Min Act: -0.1700
Data Index: 5492397 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.9941. Min Act: -0.1700
Data Index: 8121588 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.9316. Min Act: -0.1700
Data Index: 8436933 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.9316. Min Act: -0.1700
Data Index: 5321301 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.9316. Min Act: -0.1700
Data Index: 4462911 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.8066. Min Act: -0.1700
Data Index: 6048584 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.8066. Min Act: -0.1700
Data Index: 6887429 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.8066. Min Act: -0.1700
Data Index: 6232836 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.8066. Min Act: -0.1700
Data Index: 4810324 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.8066. Min Act: -0.1700
Data Index: 2885149 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.8066. Min Act: -0.1700
Data Index: 4254387 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.7441. Min Act: -0.1700
Data Index: 5071543 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.6816. Min Act: -0.1700
Data Index: 6550781 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5566. Min Range: -8.5566
Max Act: 7.7441. Min Act: -0.1700
Data Index: 6021327 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19