Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1649 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.5647. Min Act: -0.1700
Data Index: 6481160 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.3772. Min Act: -0.1700
Data Index: 5877688 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.4397. Min Act: -0.1700
Data Index: 2232673 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.3772. Min Act: -0.1700
Data Index: 7018589 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.4084. Min Act: -0.1700
Data Index: 6679329 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.3459. Min Act: -0.1700
Data Index: 962180 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.3459. Min Act: -0.1700
Data Index: 6679328 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.2522. Min Act: -0.1700
Data Index: 4356243 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.2834. Min Act: -0.1700
Data Index: 5737923 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.2834. Min Act: -0.1700
Data Index: 6462309 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.2522. Min Act: -0.1700
Data Index: 5179539 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.2522. Min Act: -0.1700
Data Index: 4365046 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.2209. Min Act: -0.1700
Data Index: 206225 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.2522. Min Act: -0.1700
Data Index: 4154869 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.2209. Min Act: -0.1700
Data Index: 82832 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.1897. Min Act: -0.1700
Data Index: 5199908 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.2209. Min Act: -0.1700
Data Index: 2825542 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.2209. Min Act: -0.1700
Data Index: 81475 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.1897. Min Act: -0.1700
Data Index: 3822309 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5647. Min Range: -5.5647
Max Act: 5.2209. Min Act: -0.1700
Data Index: 6412020 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19