Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5019 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.6481. Min Act: -0.1700
Data Index: 6226193 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.5856. Min Act: -0.1700
Data Index: 2195472 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.5231. Min Act: -0.1700
Data Index: 3108582 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.4606. Min Act: -0.1700
Data Index: 7255888 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.4606. Min Act: -0.1700
Data Index: 2831696 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.4606. Min Act: -0.1700
Data Index: 3718925 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.5231. Min Act: -0.1700
Data Index: 1263340 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3981. Min Act: -0.1700
Data Index: 8646360 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3981. Min Act: -0.1700
Data Index: 164254 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3981. Min Act: -0.1700
Data Index: 2665161 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.4606. Min Act: -0.1700
Data Index: 3108592 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3356. Min Act: -0.1700
Data Index: 944884 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3356. Min Act: -0.1700
Data Index: 8662219 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3356. Min Act: -0.1700
Data Index: 6660838 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3356. Min Act: -0.1700
Data Index: 5556754 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3356. Min Act: -0.1700
Data Index: 8207743 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2731. Min Act: -0.1700
Data Index: 8126514 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2731. Min Act: -0.1700
Data Index: 1759923 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2731. Min Act: -0.1700
Data Index: 1578529 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2731. Min Act: -0.1700
Data Index: 8164809 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19