Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.8325. Min Act: -0.1700
Data Index: 8400240 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.8325. Min Act: -0.1700
Data Index: 8169478 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.8012. Min Act: -0.1700
Data Index: 4603074 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.7699. Min Act: -0.1700
Data Index: 3090535 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.7386. Min Act: -0.1700
Data Index: 8613311 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.7386. Min Act: -0.1700
Data Index: 3995833 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.7386. Min Act: -0.1700
Data Index: 3146947 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.7074. Min Act: -0.1700
Data Index: 983625 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.7074. Min Act: -0.1700
Data Index: 7725711 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.6761. Min Act: -0.1700
Data Index: 8080152 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.6761. Min Act: -0.1700
Data Index: 1163842 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.6448. Min Act: -0.1700
Data Index: 8799378 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.6448. Min Act: -0.1700
Data Index: 2147443 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.6135. Min Act: -0.1700
Data Index: 4851813 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.6135. Min Act: -0.1700
Data Index: 2007723 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.6135. Min Act: -0.1700
Data Index: 5882236 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.6135. Min Act: -0.1700
Data Index: 5685430 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.5822. Min Act: -0.1700
Data Index: 7705010 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.5509. Min Act: -0.1700
Data Index: 2381068 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8325. Min Range: -3.8325
Max Act: 3.5822. Min Act: -0.1700
Data Index: 2541966 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19