Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2311. Min Range: -7.2311
Max Act: 7.2311. Min Act: -0.1700
Data Index: 408602 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2311. Min Range: -7.2311
Max Act: 7.1061. Min Act: -0.1700
Data Index: 6577495 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2311. Min Range: -7.2311
Max Act: 7.0436. Min Act: -0.1700
Data Index: 2661148 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.9499. Min Act: -0.1700
Data Index: 8095887 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.9186. Min Act: -0.1700
Data Index: 7643933 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.8874. Min Act: -0.1700
Data Index: 2546754 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.8561. Min Act: -0.1700
Data Index: 1717933 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.8249. Min Act: -0.1700
Data Index: 2594090 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.8249. Min Act: -0.1700
Data Index: 4007885 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.7936. Min Act: -0.1700
Data Index: 7506397 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.7936. Min Act: -0.1700
Data Index: 3319801 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.7936. Min Act: -0.1700
Data Index: 8443347 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.7936. Min Act: -0.1700
Data Index: 6031317 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.7624. Min Act: -0.1700
Data Index: 516267 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.7624. Min Act: -0.1700
Data Index: 1288758 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.7624. Min Act: -0.1700
Data Index: 3750724 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.7624. Min Act: -0.1700
Data Index: 6950482 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.7311. Min Act: -0.1700
Data Index: 8297353 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.7311. Min Act: -0.1700
Data Index: 6230627 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2311. Min Range: -7.2311
Max Act: 6.7311. Min Act: -0.1700
Data Index: 3311672 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19