Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5618. Min Range: -5.5618
Max Act: 5.5618. Min Act: -0.1700
Data Index: 7664409 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5618. Min Range: -5.5618
Max Act: 5.4368. Min Act: -0.1700
Data Index: 4470429 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5618. Min Range: -5.5618
Max Act: 5.2180. Min Act: -0.1700
Data Index: 1999167 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5618. Min Range: -5.5618
Max Act: 5.1555. Min Act: -0.1700
Data Index: 3020720 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5618. Min Range: -5.5618
Max Act: 5.1243. Min Act: -0.1700
Data Index: 1241821 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5618. Min Range: -5.5618
Max Act: 5.0930. Min Act: -0.1700
Data Index: 5514677 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5618. Min Range: -5.5618
Max Act: 5.0618. Min Act: -0.1700
Data Index: 390506 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5618. Min Range: -5.5618
Max Act: 5.0618. Min Act: -0.1700
Data Index: 3774374 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5618. Min Range: -5.5618
Max Act: 5.0305. Min Act: -0.1700
Data Index: 1528452 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5618. Min Range: -5.5618
Max Act: 5.0305. Min Act: -0.1700
Data Index: 3940555 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5618. Min Range: -5.5618
Max Act: 5.0305. Min Act: -0.1700
Data Index: 3817101 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5618. Min Range: -5.5618
Max Act: 4.9993. Min Act: -0.1700
Data Index: 7441313 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5618. Min Range: -5.5618
Max Act: 4.9993. Min Act: -0.1700
Data Index: 5567710 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5618. Min Range: -5.5618
Max Act: 4.9993. Min Act: -0.1700
Data Index: 3709406 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5618. Min Range: -5.5618
Max Act: 4.9680. Min Act: -0.1700
Data Index: 4640020 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5618. Min Range: -5.5618
Max Act: 4.9680. Min Act: -0.1700
Data Index: 7277759 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5618. Min Range: -5.5618
Max Act: 4.9680. Min Act: -0.1700
Data Index: 4045355 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5618. Min Range: -5.5618
Max Act: 4.9368. Min Act: -0.1700
Data Index: 873572 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5618. Min Range: -5.5618
Max Act: 4.9680. Min Act: -0.1700
Data Index: 2571070 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5618. Min Range: -5.5618
Max Act: 4.9680. Min Act: -0.1700
Data Index: 1195892 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19