Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 626 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.9320. Min Act: -0.1700
Data Index: 247520 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.7130. Min Act: -0.1700
Data Index: 1703749 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.6505. Min Act: -0.1700
Data Index: 1056948 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.6505. Min Act: -0.1700
Data Index: 5378844 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.6192. Min Act: -0.1700
Data Index: 5949984 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.6505. Min Act: -0.1700
Data Index: 7074333 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.6192. Min Act: -0.1700
Data Index: 6133891 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.5879. Min Act: -0.1700
Data Index: 5443548 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.5879. Min Act: -0.1700
Data Index: 2377554 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.5879. Min Act: -0.1700
Data Index: 6228787 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.5566. Min Act: -0.1700
Data Index: 2243123 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.5879. Min Act: -0.1700
Data Index: 4875605 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.5252. Min Act: -0.1700
Data Index: 8584419 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.5252. Min Act: -0.1700
Data Index: 827707 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.5252. Min Act: -0.1700
Data Index: 838306 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.5566. Min Act: -0.1700
Data Index: 1553145 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.4939. Min Act: -0.1700
Data Index: 4045060 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.4939. Min Act: -0.1700
Data Index: 1502193 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.4939. Min Act: -0.1700
Data Index: 4095436 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9320. Min Range: -3.9320
Max Act: 3.4939. Min Act: -0.1700
Data Index: 3099509 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19