Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2157. Min Range: -7.2157
Max Act: 7.2157. Min Act: -0.1700
Data Index: 3878315 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.5907. Min Act: -0.1700
Data Index: 6063177 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.5282. Min Act: -0.1700
Data Index: 6601516 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.4970. Min Act: -0.1700
Data Index: 7997043 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.2470. Min Act: -0.1700
Data Index: 508642 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.2470. Min Act: -0.1700
Data Index: 1124447 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.1845. Min Act: -0.1700
Data Index: 7428165 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.1532. Min Act: -0.1700
Data Index: 121005 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.1220. Min Act: -0.1700
Data Index: 7696956 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.1220. Min Act: -0.1700
Data Index: 5577541 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.0907. Min Act: -0.1700
Data Index: 7061828 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.0595. Min Act: -0.1700
Data Index: 1391963 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.0595. Min Act: -0.1700
Data Index: 4062049 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.0595. Min Act: -0.1700
Data Index: 4814488 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.0595. Min Act: -0.1700
Data Index: 5894804 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2157. Min Range: -7.2157
Max Act: 5.9970. Min Act: -0.1700
Data Index: 871809 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.0282. Min Act: -0.1700
Data Index: 84522 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.0282. Min Act: -0.1700
Data Index: 2677186 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.0595. Min Act: -0.1700
Data Index: 5190499 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2157. Min Range: -7.2157
Max Act: 6.0282. Min Act: -0.1700
Data Index: 8200044 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19