Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3593 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.9703. Min Act: -0.1700
Data Index: 1301417 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.8140. Min Act: -0.1700
Data Index: 4979606 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.6732. Min Act: -0.1700
Data Index: 1436251 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.5950. Min Act: -0.1700
Data Index: 2219548 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.5950. Min Act: -0.1700
Data Index: 1999897 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.5793. Min Act: -0.1700
Data Index: 3157388 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.5793. Min Act: -0.1700
Data Index: 6138080 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.5637. Min Act: -0.1700
Data Index: 3401638 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.5324. Min Act: -0.1700
Data Index: 4502314 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.5167. Min Act: -0.1700
Data Index: 3835944 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.5167. Min Act: -0.1700
Data Index: 1393642 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.4854. Min Act: -0.1700
Data Index: 8316115 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.4697. Min Act: -0.1700
Data Index: 7548065 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.4697. Min Act: -0.1700
Data Index: 1271643 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.4697. Min Act: -0.1700
Data Index: 8497520 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.4384. Min Act: -0.1700
Data Index: 272913 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.4384. Min Act: -0.1700
Data Index: 2170588 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.4541. Min Act: -0.1700
Data Index: 7138320 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.4384. Min Act: -0.1700
Data Index: 4941229 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9703. Min Range: -3.9703
Max Act: 3.4384. Min Act: -0.1700
Data Index: 6052632 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19