Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5476 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0110. Min Range: -6.0110
Max Act: 6.0110. Min Act: -0.1700
Data Index: 7641597 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.8860. Min Act: -0.1700
Data Index: 2402780 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.8548. Min Act: -0.1700
Data Index: 1375261 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.8860. Min Act: -0.1700
Data Index: 1647511 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.8235. Min Act: -0.1700
Data Index: 524797 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7610. Min Act: -0.1700
Data Index: 693409 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7610. Min Act: -0.1700
Data Index: 4759682 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7610. Min Act: -0.1700
Data Index: 4663506 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7298. Min Act: -0.1700
Data Index: 7776097 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7298. Min Act: -0.1700
Data Index: 5438124 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7298. Min Act: -0.1700
Data Index: 2081124 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7298. Min Act: -0.1700
Data Index: 2112517 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7298. Min Act: -0.1700
Data Index: 4429002 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.6985. Min Act: -0.1700
Data Index: 3560156 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.6985. Min Act: -0.1700
Data Index: 4555655 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.6985. Min Act: -0.1700
Data Index: 7191288 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.6360. Min Act: -0.1700
Data Index: 5925731 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.6360. Min Act: -0.1700
Data Index: 1343703 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.6360. Min Act: -0.1700
Data Index: 3776262 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.6360. Min Act: -0.1700
Data Index: 4605423 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19