Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2417 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.9185. Min Act: -0.1700
Data Index: 2104039 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.6997. Min Act: -0.1700
Data Index: 6462286 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.6372. Min Act: -0.1700
Data Index: 5198863 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.6685. Min Act: -0.1700
Data Index: 3102877 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.6372. Min Act: -0.1700
Data Index: 3368529 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.5747. Min Act: -0.1700
Data Index: 2490625 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.5435. Min Act: -0.1700
Data Index: 4149661 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.5122. Min Act: -0.1700
Data Index: 3265726 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.5122. Min Act: -0.1700
Data Index: 1267967 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.5122. Min Act: -0.1700
Data Index: 6026373 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.5122. Min Act: -0.1700
Data Index: 2476927 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.5122. Min Act: -0.1700
Data Index: 1903879 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.4810. Min Act: -0.1700
Data Index: 7480710 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.4810. Min Act: -0.1700
Data Index: 6086875 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.4810. Min Act: -0.1700
Data Index: 627464 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.4497. Min Act: -0.1700
Data Index: 8552530 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.4497. Min Act: -0.1700
Data Index: 2923481 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.4185. Min Act: -0.1700
Data Index: 1012127 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.4185. Min Act: -0.1700
Data Index: 3373693 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9185. Min Range: -6.9185
Max Act: 6.4185. Min Act: -0.1700
Data Index: 880096 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19