Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4910 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.8339. Min Act: -0.1700
Data Index: 880951 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.8027. Min Act: -0.1700
Data Index: 7648090 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.6777. Min Act: -0.1700
Data Index: 8469038 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.6777. Min Act: -0.1700
Data Index: 3342904 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.6152. Min Act: -0.1700
Data Index: 2882807 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.5527. Min Act: -0.1700
Data Index: 2064281 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.4902. Min Act: -0.1700
Data Index: 549588 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.4902. Min Act: -0.1700
Data Index: 8084496 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.4589. Min Act: -0.1700
Data Index: 8780921 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.4902. Min Act: -0.1700
Data Index: 8691369 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.4589. Min Act: -0.1700
Data Index: 2854980 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.4277. Min Act: -0.1700
Data Index: 2017128 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.4277. Min Act: -0.1700
Data Index: 1750848 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.4277. Min Act: -0.1700
Data Index: 605572 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.4277. Min Act: -0.1700
Data Index: 8165057 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.4277. Min Act: -0.1700
Data Index: 5010741 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.4589. Min Act: -0.1700
Data Index: 6530996 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.3964. Min Act: -0.1700
Data Index: 3486769 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.3964. Min Act: -0.1700
Data Index: 1316991 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8339. Min Range: -5.8339
Max Act: 5.3964. Min Act: -0.1700
Data Index: 6839778 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19