Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5330 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2956. Min Range: -8.2956
Max Act: 8.2956. Min Act: -0.1700
Data Index: 4556995 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2956. Min Range: -8.2956
Max Act: 8.2331. Min Act: -0.1700
Data Index: 1735523 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.9206. Min Act: -0.1700
Data Index: 4556997 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.9206. Min Act: -0.1700
Data Index: 4280354 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.7956. Min Act: -0.1700
Data Index: 1189051 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.7644. Min Act: -0.1700
Data Index: 1865535 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.7644. Min Act: -0.1700
Data Index: 3209394 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.5769. Min Act: -0.1700
Data Index: 1285145 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.5456. Min Act: -0.1700
Data Index: 4014436 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.5456. Min Act: -0.1700
Data Index: 6654601 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.5456. Min Act: -0.1700
Data Index: 2806923 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.5144. Min Act: -0.1700
Data Index: 5271281 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.5144. Min Act: -0.1700
Data Index: 1324266 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.5144. Min Act: -0.1700
Data Index: 2119322 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.5144. Min Act: -0.1700
Data Index: 94777 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.4831. Min Act: -0.1700
Data Index: 3608861 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.4831. Min Act: -0.1700
Data Index: 2795299 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.4519. Min Act: -0.1700
Data Index: 3457481 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.4519. Min Act: -0.1700
Data Index: 1764111 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2956. Min Range: -8.2956
Max Act: 7.4519. Min Act: -0.1700
Data Index: 5207864 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19