Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.3870. Min Act: -0.1700
Data Index: 6897064 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.4340. Min Act: -0.1700
Data Index: 6448326 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.3713. Min Act: -0.1700
Data Index: 1139986 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.3243. Min Act: -0.1700
Data Index: 4027704 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.2615. Min Act: -0.1700
Data Index: 6501247 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.2143. Min Act: -0.1700
Data Index: 4665323 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.2300. Min Act: -0.1700
Data Index: 117152 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.2143. Min Act: -0.1700
Data Index: 4665322 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.2143. Min Act: -0.1700
Data Index: 7177188 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.1986. Min Act: -0.1700
Data Index: 7771745 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.1514. Min Act: -0.1700
Data Index: 457012 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.1829. Min Act: -0.1700
Data Index: 6501246 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.1671. Min Act: -0.1700
Data Index: 3710620 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.1514. Min Act: -0.1700
Data Index: 1063450 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.1357. Min Act: -0.1700
Data Index: 3186894 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.1357. Min Act: -0.1700
Data Index: 7185376 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.1041. Min Act: -0.1700
Data Index: 6285012 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.1041. Min Act: -0.1700
Data Index: 2256198 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.1041. Min Act: -0.1700
Data Index: 8207876 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4340. Min Range: -3.4340
Max Act: 3.1041. Min Act: -0.1700
Data Index: 8288013 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19