Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5218 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3135. Min Range: -9.3135
Max Act: 9.3135. Min Act: -0.1700
Data Index: 3641421 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3135. Min Range: -9.3135
Max Act: 9.2510. Min Act: -0.1700
Data Index: 231602 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3135. Min Range: -9.3135
Max Act: 9.2510. Min Act: -0.1700
Data Index: 3220944 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3135. Min Range: -9.3135
Max Act: 9.1885. Min Act: -0.1700
Data Index: 448618 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.8760. Min Act: -0.1700
Data Index: 8831207 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.8135. Min Act: -0.1700
Data Index: 3630999 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.7510. Min Act: -0.1700
Data Index: 3757508 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.7510. Min Act: -0.1700
Data Index: 2846712 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.6885. Min Act: -0.1700
Data Index: 8558936 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.6885. Min Act: -0.1700
Data Index: 6668147 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.6885. Min Act: -0.1700
Data Index: 2303119 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.6885. Min Act: -0.1700
Data Index: 1964157 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.6885. Min Act: -0.1700
Data Index: 4447117 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.6260. Min Act: -0.1700
Data Index: 1478824 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.6260. Min Act: -0.1700
Data Index: 3977247 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.6260. Min Act: -0.1700
Data Index: 3574225 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.5635. Min Act: -0.1700
Data Index: 8469938 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.5635. Min Act: -0.1700
Data Index: 401551 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.5010. Min Act: -0.1700
Data Index: 1969270 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3135. Min Range: -9.3135
Max Act: 8.5635. Min Act: -0.1700
Data Index: 2018724 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19