Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.5238. Min Act: -0.1700
Data Index: 3886565 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.4611. Min Act: -0.1700
Data Index: 3886566 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.4298. Min Act: -0.1700
Data Index: 3718185 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.3984. Min Act: -0.1700
Data Index: 3718187 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.2100. Min Act: -0.1700
Data Index: 3718188 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.2100. Min Act: -0.1700
Data Index: 3886563 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.0683. Min Act: -0.1700
Data Index: 3718186 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.0525. Min Act: -0.1700
Data Index: 3813213 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.0210. Min Act: -0.1700
Data Index: 3886564 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.0210. Min Act: -0.1700
Data Index: 4551871 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.0210. Min Act: -0.1699
Data Index: 4148476 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.0052. Min Act: -0.1700
Data Index: 597230 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5238. Min Range: -3.5238
Max Act: 3.0052. Min Act: -0.1700
Data Index: 5582616 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5238. Min Range: -3.5238
Max Act: 2.9736. Min Act: -0.1700
Data Index: 3594173 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5238. Min Range: -3.5238
Max Act: 2.9736. Min Act: -0.1700
Data Index: 597229 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5238. Min Range: -3.5238
Max Act: 2.9577. Min Act: -0.1700
Data Index: 3644628 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5238. Min Range: -3.5238
Max Act: 2.9419. Min Act: -0.1695
Data Index: 1551464 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5238. Min Range: -3.5238
Max Act: 2.9577. Min Act: -0.1700
Data Index: 5324410 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5238. Min Range: -3.5238
Max Act: 2.9577. Min Act: -0.1700
Data Index: 8627112 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5238. Min Range: -3.5238
Max Act: 2.9261. Min Act: -0.1697
Data Index: 5339551 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19