Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5152 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4026. Min Range: -9.4026
Max Act: 9.4026. Min Act: -0.1700
Data Index: 3554153 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.6526. Min Act: -0.1700
Data Index: 3115217 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.3401. Min Act: -0.1700
Data Index: 4264369 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.3401. Min Act: -0.1700
Data Index: 3480490 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.2776. Min Act: -0.1700
Data Index: 7017403 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.2776. Min Act: -0.1700
Data Index: 6613324 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.2151. Min Act: -0.1700
Data Index: 6150113 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.2151. Min Act: -0.1700
Data Index: 3198733 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.1839. Min Act: -0.1700
Data Index: 6112646 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.1526. Min Act: -0.1700
Data Index: 4888210 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.1839. Min Act: -0.1700
Data Index: 161054 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.0901. Min Act: -0.1700
Data Index: 5573337 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.0589. Min Act: -0.1700
Data Index: 2390805 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.0589. Min Act: -0.1700
Data Index: 3373495 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4026. Min Range: -9.4026
Max Act: 7.9964. Min Act: -0.1700
Data Index: 8311952 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4026. Min Range: -9.4026
Max Act: 8.0276. Min Act: -0.1700
Data Index: 5541974 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4026. Min Range: -9.4026
Max Act: 7.9964. Min Act: -0.1700
Data Index: 5228784 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4026. Min Range: -9.4026
Max Act: 7.9651. Min Act: -0.1700
Data Index: 7605671 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4026. Min Range: -9.4026
Max Act: 7.9651. Min Act: -0.1700
Data Index: 7529837 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4026. Min Range: -9.4026
Max Act: 7.9339. Min Act: -0.1700
Data Index: 7367210 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19