Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 746 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.7741. Min Act: -0.1700
Data Index: 7380923 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.7428. Min Act: -0.1700
Data Index: 8827192 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.4303. Min Act: -0.1700
Data Index: 8225174 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.4303. Min Act: -0.1700
Data Index: 4872433 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.3991. Min Act: -0.1700
Data Index: 1178432 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.3991. Min Act: -0.1700
Data Index: 5911806 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.3991. Min Act: -0.1700
Data Index: 6567099 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.3053. Min Act: -0.1700
Data Index: 8465910 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.3053. Min Act: -0.1700
Data Index: 1546028 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.3053. Min Act: -0.1700
Data Index: 6968221 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.3053. Min Act: -0.1700
Data Index: 1325646 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.2740. Min Act: -0.1700
Data Index: 6454425 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.2740. Min Act: -0.1700
Data Index: 8023096 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.2740. Min Act: -0.1700
Data Index: 2281314 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.3053. Min Act: -0.1700
Data Index: 5611298 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.2428. Min Act: -0.1700
Data Index: 5320223 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.2740. Min Act: -0.1700
Data Index: 6349215 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.2428. Min Act: -0.1700
Data Index: 1329830 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.2428. Min Act: -0.1700
Data Index: 1943320 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.2428. Min Act: -0.1700
Data Index: 881474 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19