Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 684 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.5383. Min Act: -0.1700
Data Index: 1364264 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.5383. Min Act: -0.1700
Data Index: 2355690 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.5070. Min Act: -0.1700
Data Index: 1943951 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.3820. Min Act: -0.1700
Data Index: 3809202 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.3508. Min Act: -0.1699
Data Index: 5647487 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.3508. Min Act: -0.1700
Data Index: 2943308 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.3195. Min Act: -0.1700
Data Index: 4094788 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.3195. Min Act: -0.1700
Data Index: 1351612 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.2883. Min Act: -0.1700
Data Index: 1561608 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.2883. Min Act: -0.1700
Data Index: 418168 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.2883. Min Act: -0.1700
Data Index: 1196842 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.2883. Min Act: -0.1700
Data Index: 5992004 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.2258. Min Act: -0.1700
Data Index: 7989303 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.2570. Min Act: -0.1698
Data Index: 2031054 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.2570. Min Act: -0.1699
Data Index: 2894353 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.2570. Min Act: -0.1700
Data Index: 7743027 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.2258. Min Act: -0.1700
Data Index: 8165706 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.2570. Min Act: -0.1700
Data Index: 6415833 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.2570. Min Act: -0.1700
Data Index: 6041319 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5383. Min Range: -5.5383
Max Act: 5.2258. Min Act: -0.1700
Data Index: 1706408 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19