Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4925 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0609. Min Range: -3.0609
Max Act: 3.0609. Min Act: -0.1700
Data Index: 7687750 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0609. Min Range: -3.0609
Max Act: 3.0136. Min Act: -0.1700
Data Index: 6000306 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9661. Min Act: -0.1700
Data Index: 8503303 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9503. Min Act: -0.1700
Data Index: 4446787 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9503. Min Act: -0.1700
Data Index: 5014401 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9503. Min Act: -0.1700
Data Index: 5435288 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9345. Min Act: -0.1700
Data Index: 8607435 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9345. Min Act: -0.1700
Data Index: 1387677 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9503. Min Act: -0.1700
Data Index: 6080506 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9345. Min Act: -0.1700
Data Index: 1641491 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9345. Min Act: -0.1700
Data Index: 1193354 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9028. Min Act: -0.1700
Data Index: 8016250 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9028. Min Act: -0.1700
Data Index: 589446 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9186. Min Act: -0.1700
Data Index: 3078351 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9186. Min Act: -0.1700
Data Index: 2142061 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9028. Min Act: -0.1700
Data Index: 7764911 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.9028. Min Act: -0.1700
Data Index: 3164794 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.8869. Min Act: -0.1700
Data Index: 7697764 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.8711. Min Act: -0.1700
Data Index: 2620984 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0609. Min Range: -3.0609
Max Act: 2.8711. Min Act: -0.1700
Data Index: 7853480 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19