Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.3722. Min Act: -0.1700
Data Index: 4588589 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.2784. Min Act: -0.1700
Data Index: 3169114 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.2784. Min Act: -0.1700
Data Index: 7609459 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.2159. Min Act: -0.1700
Data Index: 4713531 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.1534. Min Act: -0.1700
Data Index: 3969075 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.0909. Min Act: -0.1700
Data Index: 5642062 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.1222. Min Act: -0.1700
Data Index: 188868 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.0909. Min Act: -0.1700
Data Index: 6145490 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.0597. Min Act: -0.1700
Data Index: 6296195 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.0597. Min Act: -0.1700
Data Index: 3415680 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.0597. Min Act: -0.1700
Data Index: 4958120 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.0284. Min Act: -0.1700
Data Index: 1446063 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.0284. Min Act: -0.1700
Data Index: 3753508 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.0284. Min Act: -0.1700
Data Index: 3003418 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.0284. Min Act: -0.1700
Data Index: 1359802 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3722. Min Range: -6.3722
Max Act: 6.0284. Min Act: -0.1700
Data Index: 4114829 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3722. Min Range: -6.3722
Max Act: 5.9972. Min Act: -0.1700
Data Index: 1445580 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3722. Min Range: -6.3722
Max Act: 5.9972. Min Act: -0.1700
Data Index: 6055684 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3722. Min Range: -6.3722
Max Act: 5.9972. Min Act: -0.1700
Data Index: 4288416 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3722. Min Range: -6.3722
Max Act: 5.9972. Min Act: -0.1700
Data Index: 8736880 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19