Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2196 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2191. Min Range: -6.2191
Max Act: 6.2191. Min Act: -0.1700
Data Index: 5844023 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2191. Min Range: -6.2191
Max Act: 6.0003. Min Act: -0.1700
Data Index: 1510296 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.7503. Min Act: -0.1700
Data Index: 5357482 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.7503. Min Act: -0.1700
Data Index: 7677453 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.6253. Min Act: -0.1700
Data Index: 8003702 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.6253. Min Act: -0.1700
Data Index: 7900956 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.5941. Min Act: -0.1700
Data Index: 8550986 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.5316. Min Act: -0.1700
Data Index: 2224050 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.5316. Min Act: -0.1700
Data Index: 631205 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.5316. Min Act: -0.1700
Data Index: 6941380 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.4066. Min Act: -0.1700
Data Index: 5156052 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.3753. Min Act: -0.1700
Data Index: 992716 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.4066. Min Act: -0.1700
Data Index: 2212984 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.3753. Min Act: -0.1700
Data Index: 6069185 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.4066. Min Act: -0.1700
Data Index: 4126903 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.3753. Min Act: -0.1700
Data Index: 3245254 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.3128. Min Act: -0.1700
Data Index: 1589606 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.3128. Min Act: -0.1700
Data Index: 5263688 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.3128. Min Act: -0.1700
Data Index: 6989419 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2191. Min Range: -6.2191
Max Act: 5.3128. Min Act: -0.1700
Data Index: 8528884 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19