Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3686 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6160. Min Range: -5.6160
Max Act: 5.6160. Min Act: -0.1700
Data Index: 8822979 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.9598. Min Act: -0.1700
Data Index: 6887102 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.9598. Min Act: -0.1700
Data Index: 7622558 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.9285. Min Act: -0.1700
Data Index: 1527216 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.8973. Min Act: -0.1700
Data Index: 4652656 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.8973. Min Act: -0.1700
Data Index: 6804168 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.8660. Min Act: -0.1700
Data Index: 433060 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.8660. Min Act: -0.1700
Data Index: 8767841 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.8660. Min Act: -0.1700
Data Index: 2353353 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.8035. Min Act: -0.1700
Data Index: 2280414 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.7723. Min Act: -0.1700
Data Index: 4158806 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.7723. Min Act: -0.1700
Data Index: 733599 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.7410. Min Act: -0.1700
Data Index: 4946230 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.7723. Min Act: -0.1700
Data Index: 4854419 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.7410. Min Act: -0.1700
Data Index: 2996543 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.7410. Min Act: -0.1700
Data Index: 8803958 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.7410. Min Act: -0.1700
Data Index: 3552958 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.7098. Min Act: -0.1700
Data Index: 8138801 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.7098. Min Act: -0.1700
Data Index: 2553492 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6160. Min Range: -5.6160
Max Act: 4.7098. Min Act: -0.1700
Data Index: 8366250 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19