Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 696 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2609. Min Range: -6.2609
Max Act: 6.2609. Min Act: -0.1700
Data Index: 8210014 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2609. Min Range: -6.2609
Max Act: 6.1359. Min Act: -0.1700
Data Index: 8677875 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2609. Min Range: -6.2609
Max Act: 6.0421. Min Act: -0.1700
Data Index: 1259218 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2609. Min Range: -6.2609
Max Act: 6.0421. Min Act: -0.1700
Data Index: 3680985 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2609. Min Range: -6.2609
Max Act: 6.0421. Min Act: -0.1700
Data Index: 5884623 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.9171. Min Act: -0.1700
Data Index: 7955201 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.8546. Min Act: -0.1700
Data Index: 6696841 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.7921. Min Act: -0.1700
Data Index: 6449839 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.7921. Min Act: -0.1700
Data Index: 111782 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.7296. Min Act: -0.1700
Data Index: 1792402 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.6671. Min Act: -0.1700
Data Index: 7067717 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.6359. Min Act: -0.1700
Data Index: 6394091 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.6359. Min Act: -0.1700
Data Index: 1792397 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.6671. Min Act: -0.1700
Data Index: 525291 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.6359. Min Act: -0.1700
Data Index: 6330726 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.5734. Min Act: -0.1700
Data Index: 1301475 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.5421. Min Act: -0.1700
Data Index: 5637556 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.5421. Min Act: -0.1700
Data Index: 5767136 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.5421. Min Act: -0.1700
Data Index: 7498549 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2609. Min Range: -6.2609
Max Act: 5.5421. Min Act: -0.1700
Data Index: 5713802 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19