Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 278 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4324. Min Range: -10.4324
Max Act: 10.4324. Min Act: -0.1700
Data Index: 5206458 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4324. Min Range: -10.4324
Max Act: 10.3074. Min Act: -0.1700
Data Index: 7080550 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4324. Min Range: -10.4324
Max Act: 10.3699. Min Act: -0.1700
Data Index: 5716124 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.8074. Min Act: -0.1700
Data Index: 7425122 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.7449. Min Act: -0.1700
Data Index: 1189891 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.7449. Min Act: -0.1700
Data Index: 4467180 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.7449. Min Act: -0.1700
Data Index: 322308 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.6824. Min Act: -0.1700
Data Index: 1747619 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.6824. Min Act: -0.1700
Data Index: 8541510 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.5574. Min Act: -0.1700
Data Index: 224877 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.5574. Min Act: -0.1700
Data Index: 5702454 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.5574. Min Act: -0.1700
Data Index: 2432084 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.5574. Min Act: -0.1700
Data Index: 1645128 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.5574. Min Act: -0.1700
Data Index: 1055049 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.5574. Min Act: -0.1700
Data Index: 6389787 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.4949. Min Act: -0.1700
Data Index: 1679767 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.4324. Min Act: -0.1700
Data Index: 265567 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.3699. Min Act: -0.1700
Data Index: 1975716 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.3699. Min Act: -0.1700
Data Index: 721150 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4324. Min Range: -10.4324
Max Act: 9.3699. Min Act: -0.1700
Data Index: 5713588 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19