Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.9249. Min Act: -0.1700
Data Index: 6921190 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.7999. Min Act: -0.1700
Data Index: 1135624 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.7374. Min Act: -0.1700
Data Index: 6815376 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.5499. Min Act: -0.1700
Data Index: 1764640 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.4249. Min Act: -0.1700
Data Index: 4582889 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.6124. Min Act: -0.1700
Data Index: 6393806 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.4249. Min Act: -0.1700
Data Index: 335103 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.3624. Min Act: -0.1700
Data Index: 1152792 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.3624. Min Act: -0.1700
Data Index: 3230242 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.2374. Min Act: -0.1700
Data Index: 5886464 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.2374. Min Act: -0.1700
Data Index: 4971586 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.2374. Min Act: -0.1700
Data Index: 2172968 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.1749. Min Act: -0.1700
Data Index: 1661321 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.1124. Min Act: -0.1700
Data Index: 4984572 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.1749. Min Act: -0.1700
Data Index: 3768264 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.1124. Min Act: -0.1700
Data Index: 3280559 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.0499. Min Act: -0.1700
Data Index: 4900599 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.0499. Min Act: -0.1700
Data Index: 5077373 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.1124. Min Act: -0.1700
Data Index: 2099477 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9249. Min Range: -9.9249
Max Act: 9.0499. Min Act: -0.1700
Data Index: 3336062 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19