Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.7300. Min Act: -0.1700
Data Index: 8192318 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.6050. Min Act: -0.1700
Data Index: 3818757 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.5738. Min Act: -0.1700
Data Index: 2021100 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.5425. Min Act: -0.1700
Data Index: 6166146 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.5738. Min Act: -0.1700
Data Index: 1795304 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.5425. Min Act: -0.1700
Data Index: 403489 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.5425. Min Act: -0.1700
Data Index: 6496805 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.4488. Min Act: -0.1700
Data Index: 1379887 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.4488. Min Act: -0.1700
Data Index: 540901 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.4488. Min Act: -0.1700
Data Index: 2619177 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.4488. Min Act: -0.1700
Data Index: 6072020 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.4488. Min Act: -0.1700
Data Index: 2542376 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.4175. Min Act: -0.1700
Data Index: 5679134 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.4175. Min Act: -0.1700
Data Index: 8577368 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.4175. Min Act: -0.1700
Data Index: 4472541 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.4175. Min Act: -0.1700
Data Index: 2533088 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.4175. Min Act: -0.1700
Data Index: 8632757 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.4175. Min Act: -0.1700
Data Index: 5749647 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.3863. Min Act: -0.1700
Data Index: 7958168 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7300. Min Range: -5.7300
Max Act: 5.3550. Min Act: -0.1700
Data Index: 8053237 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19