Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.6241. Min Act: -0.1700
Data Index: 4549219 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.6241. Min Act: -0.1700
Data Index: 4973438 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.5928. Min Act: -0.1700
Data Index: 4623547 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.6241. Min Act: -0.1700
Data Index: 8824897 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.5616. Min Act: -0.1700
Data Index: 6303663 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.5303. Min Act: -0.1700
Data Index: 4544592 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.5616. Min Act: -0.1700
Data Index: 3019757 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.4991. Min Act: -0.1700
Data Index: 7548416 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.5303. Min Act: -0.1700
Data Index: 4027525 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.5303. Min Act: -0.1700
Data Index: 8414873 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.4991. Min Act: -0.1700
Data Index: 4918922 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.4991. Min Act: -0.1700
Data Index: 1018105 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.4678. Min Act: -0.1700
Data Index: 7350316 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.4678. Min Act: -0.1700
Data Index: 982211 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.4991. Min Act: -0.1700
Data Index: 5282077 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.4678. Min Act: -0.1700
Data Index: 399605 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.4678. Min Act: -0.1700
Data Index: 4907189 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.4366. Min Act: -0.1700
Data Index: 3294583 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.4053. Min Act: -0.1700
Data Index: 1424164 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6241. Min Range: -4.6241
Max Act: 4.4366. Min Act: -0.1700
Data Index: 1124403 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19