Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3537 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.6964. Min Act: -0.1700
Data Index: 3118019 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.5401. Min Act: -0.1700
Data Index: 1888160 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.3214. Min Act: -0.1700
Data Index: 6584049 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.2276. Min Act: -0.1700
Data Index: 1915794 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.2276. Min Act: -0.1700
Data Index: 922937 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.2276. Min Act: -0.1700
Data Index: 6823745 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.2276. Min Act: -0.1700
Data Index: 8463728 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.1964. Min Act: -0.1700
Data Index: 5406146 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.1964. Min Act: -0.1700
Data Index: 543558 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.2276. Min Act: -0.1700
Data Index: 5518099 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.1964. Min Act: -0.1700
Data Index: 6484530 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.1339. Min Act: -0.1700
Data Index: 5784805 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.1339. Min Act: -0.1700
Data Index: 7382259 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.1026. Min Act: -0.1700
Data Index: 5262055 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.1026. Min Act: -0.1700
Data Index: 4351898 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.0714. Min Act: -0.1700
Data Index: 7111122 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.0714. Min Act: -0.1700
Data Index: 7660479 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.0714. Min Act: -0.1700
Data Index: 6090238 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.0714. Min Act: -0.1700
Data Index: 63430 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6964. Min Range: -7.6964
Max Act: 7.0089. Min Act: -0.1700
Data Index: 1950375 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19