Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2020 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.5780. Min Act: -0.1700
Data Index: 8012668 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.5155. Min Act: -0.1700
Data Index: 7449961 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4843. Min Act: -0.1698
Data Index: 8786270 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4843. Min Act: -0.1700
Data Index: 6696147 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4530. Min Act: -0.1700
Data Index: 4898373 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4530. Min Act: -0.1700
Data Index: 1981652 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4530. Min Act: -0.1700
Data Index: 5185079 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4218. Min Act: -0.1700
Data Index: 3497033 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4218. Min Act: -0.1700
Data Index: 8639642 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4530. Min Act: -0.1700
Data Index: 7906224 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4218. Min Act: -0.1700
Data Index: 2308998 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.3905. Min Act: -0.1698
Data Index: 193910 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4218. Min Act: -0.1700
Data Index: 51788 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4218. Min Act: -0.1700
Data Index: 8079169 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4218. Min Act: -0.1700
Data Index: 2351439 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.4218. Min Act: -0.1700
Data Index: 7706111 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.3593. Min Act: -0.1699
Data Index: 2269099 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.3905. Min Act: -0.1700
Data Index: 77498 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.3593. Min Act: -0.1700
Data Index: 4972272 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5780. Min Range: -5.5780
Max Act: 5.3905. Min Act: -0.1700
Data Index: 4156354 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19