Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0026. Min Range: -7.0026
Max Act: 7.0026. Min Act: -0.1700
Data Index: 3006369 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.5026. Min Act: -0.1700
Data Index: 7063679 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.4401. Min Act: -0.1700
Data Index: 4173852 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.3776. Min Act: -0.1700
Data Index: 199511 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.3464. Min Act: -0.1700
Data Index: 6259369 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.3464. Min Act: -0.1700
Data Index: 4903371 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.3464. Min Act: -0.1700
Data Index: 8766744 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.3464. Min Act: -0.1700
Data Index: 4163467 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.3151. Min Act: -0.1700
Data Index: 4488861 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.3464. Min Act: -0.1700
Data Index: 764903 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.2214. Min Act: -0.1700
Data Index: 1653562 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.2526. Min Act: -0.1700
Data Index: 8165302 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.2214. Min Act: -0.1700
Data Index: 4356255 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.1901. Min Act: -0.1700
Data Index: 144015 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.2214. Min Act: -0.1700
Data Index: 6209227 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.1901. Min Act: -0.1700
Data Index: 1149673 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.1589. Min Act: -0.1700
Data Index: 1354792 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.1589. Min Act: -0.1700
Data Index: 122562 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.1589. Min Act: -0.1700
Data Index: 142195 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0026. Min Range: -7.0026
Max Act: 6.1276. Min Act: -0.1700
Data Index: 8303871 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19