Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4220 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.4402. Min Act: -0.1700
Data Index: 178902 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.3777. Min Act: -0.1700
Data Index: 3674215 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.3777. Min Act: -0.1700
Data Index: 3174570 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.3777. Min Act: -0.1700
Data Index: 472138 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.3777. Min Act: -0.1700
Data Index: 1470511 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.3777. Min Act: -0.1700
Data Index: 1947147 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.3465. Min Act: -0.1700
Data Index: 2387632 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.3465. Min Act: -0.1700
Data Index: 554122 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.3152. Min Act: -0.1700
Data Index: 8723242 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.3465. Min Act: -0.1700
Data Index: 8271556 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.3152. Min Act: -0.1700
Data Index: 2825891 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.3152. Min Act: -0.1700
Data Index: 1331689 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.2840. Min Act: -0.1700
Data Index: 1805637 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.2840. Min Act: -0.1700
Data Index: 8024276 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.2840. Min Act: -0.1700
Data Index: 4644250 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.2840. Min Act: -0.1700
Data Index: 5991125 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.2527. Min Act: -0.1700
Data Index: 1325617 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.2527. Min Act: -0.1700
Data Index: 7509619 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.2527. Min Act: -0.1700
Data Index: 8514222 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4402. Min Range: -6.4402
Max Act: 6.2215. Min Act: -0.1700
Data Index: 552929 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19