Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4733 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0130. Min Range: -9.0130
Max Act: 9.0130. Min Act: -0.1700
Data Index: 737187 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0130. Min Range: -9.0130
Max Act: 9.0130. Min Act: -0.1700
Data Index: 8180244 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.8255. Min Act: -0.1700
Data Index: 1208340 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.7630. Min Act: -0.1700
Data Index: 588603 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.7630. Min Act: -0.1700
Data Index: 273769 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.7630. Min Act: -0.1700
Data Index: 708500 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.7005. Min Act: -0.1700
Data Index: 7683395 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.6380. Min Act: -0.1700
Data Index: 7589997 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.6380. Min Act: -0.1700
Data Index: 2770131 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.6380. Min Act: -0.1700
Data Index: 8540655 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.5755. Min Act: -0.1700
Data Index: 8035653 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.5755. Min Act: -0.1700
Data Index: 6248357 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.5130. Min Act: -0.1700
Data Index: 4709290 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.5755. Min Act: -0.1700
Data Index: 2505586 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.5130. Min Act: -0.1700
Data Index: 2613581 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.5130. Min Act: -0.1700
Data Index: 3817953 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.5130. Min Act: -0.1700
Data Index: 5679410 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.4505. Min Act: -0.1700
Data Index: 5717065 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.4505. Min Act: -0.1700
Data Index: 6939268 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0130. Min Range: -9.0130
Max Act: 8.4505. Min Act: -0.1700
Data Index: 7248566 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19