Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1631 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1220. Min Range: -9.1220
Max Act: 9.1220. Min Act: -0.1700
Data Index: 1095510 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.5595. Min Act: -0.1700
Data Index: 880151 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.4970. Min Act: -0.1700
Data Index: 3112586 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.4345. Min Act: -0.1700
Data Index: 446371 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.4345. Min Act: -0.1700
Data Index: 637673 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.3720. Min Act: -0.1700
Data Index: 8192620 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.3720. Min Act: -0.1700
Data Index: 2524210 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.3720. Min Act: -0.1700
Data Index: 6301864 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.2470. Min Act: -0.1700
Data Index: 2764061 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.3095. Min Act: -0.1700
Data Index: 930672 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.2470. Min Act: -0.1700
Data Index: 3039814 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.2470. Min Act: -0.1700
Data Index: 8182 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.2470. Min Act: -0.1700
Data Index: 5707262 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.1845. Min Act: -0.1700
Data Index: 6828101 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.1845. Min Act: -0.1700
Data Index: 66528 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.1845. Min Act: -0.1700
Data Index: 4415637 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.2470. Min Act: -0.1700
Data Index: 8574205 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.1220. Min Act: -0.1700
Data Index: 197429 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.1220. Min Act: -0.1700
Data Index: 1650774 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1220. Min Range: -9.1220
Max Act: 8.1220. Min Act: -0.1700
Data Index: 3890802 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19