Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4865. Min Range: -6.4865
Max Act: 6.4865. Min Act: -0.1700
Data Index: 7119214 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4865. Min Range: -6.4865
Max Act: 6.3615. Min Act: -0.1700
Data Index: 3436841 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4865. Min Range: -6.4865
Max Act: 6.2990. Min Act: -0.1700
Data Index: 1049378 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4865. Min Range: -6.4865
Max Act: 6.2052. Min Act: -0.1700
Data Index: 7099066 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4865. Min Range: -6.4865
Max Act: 6.1115. Min Act: -0.1700
Data Index: 252054 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4865. Min Range: -6.4865
Max Act: 6.0802. Min Act: -0.1700
Data Index: 871131 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.9865. Min Act: -0.1700
Data Index: 1633808 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.9865. Min Act: -0.1700
Data Index: 4881817 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.9552. Min Act: -0.1700
Data Index: 5392371 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.9552. Min Act: -0.1700
Data Index: 2479951 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.9865. Min Act: -0.1700
Data Index: 6419376 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.8927. Min Act: -0.1700
Data Index: 3010039 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.8927. Min Act: -0.1700
Data Index: 1299629 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.8615. Min Act: -0.1700
Data Index: 991454 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.8615. Min Act: -0.1700
Data Index: 1851660 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.8302. Min Act: -0.1700
Data Index: 7893798 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.8615. Min Act: -0.1700
Data Index: 7178407 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.8302. Min Act: -0.1700
Data Index: 1329867 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.7990. Min Act: -0.1700
Data Index: 6504224 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4865. Min Range: -6.4865
Max Act: 5.7677. Min Act: -0.1700
Data Index: 44935 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19