Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.6006. Min Act: -0.1700
Data Index: 8255504 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.5381. Min Act: -0.1700
Data Index: 4033976 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.4756. Min Act: -0.1700
Data Index: 6620202 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.4756. Min Act: -0.1700
Data Index: 7528680 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.4443. Min Act: -0.1700
Data Index: 2708301 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.4131. Min Act: -0.1700
Data Index: 4542868 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.4443. Min Act: -0.1700
Data Index: 1792929 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.4131. Min Act: -0.1700
Data Index: 5986264 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.3818. Min Act: -0.1700
Data Index: 591021 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.4131. Min Act: -0.1700
Data Index: 49307 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.4131. Min Act: -0.1700
Data Index: 3600681 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.3818. Min Act: -0.1700
Data Index: 1551346 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.3818. Min Act: -0.1700
Data Index: 7712946 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.3818. Min Act: -0.1700
Data Index: 924446 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.3506. Min Act: -0.1700
Data Index: 5191306 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.3193. Min Act: -0.1700
Data Index: 8169445 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.3193. Min Act: -0.1700
Data Index: 3352704 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.3193. Min Act: -0.1700
Data Index: 1121520 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.3193. Min Act: -0.1700
Data Index: 1629868 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6006. Min Range: -4.6006
Max Act: 4.3193. Min Act: -0.1700
Data Index: 4768161 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19