Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6599. Min Range: -7.6599
Max Act: 7.6599. Min Act: -0.1700
Data Index: 1904182 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6599. Min Range: -7.6599
Max Act: 7.1911. Min Act: -0.1700
Data Index: 5807254 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6599. Min Range: -7.6599
Max Act: 7.1911. Min Act: -0.1700
Data Index: 634003 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6599. Min Range: -7.6599
Max Act: 7.0974. Min Act: -0.1700
Data Index: 3617969 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6599. Min Range: -7.6599
Max Act: 7.0349. Min Act: -0.1700
Data Index: 4304056 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.9724. Min Act: -0.1700
Data Index: 2227623 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.9724. Min Act: -0.1700
Data Index: 7933903 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.9411. Min Act: -0.1700
Data Index: 4226839 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.9411. Min Act: -0.1700
Data Index: 8178988 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.8161. Min Act: -0.1700
Data Index: 8129815 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.8474. Min Act: -0.1700
Data Index: 4304048 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.8161. Min Act: -0.1700
Data Index: 7041520 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.7849. Min Act: -0.1700
Data Index: 619600 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.7849. Min Act: -0.1700
Data Index: 2144478 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.7849. Min Act: -0.1700
Data Index: 5070911 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.7536. Min Act: -0.1700
Data Index: 5700201 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.7224. Min Act: -0.1700
Data Index: 3125910 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.7536. Min Act: -0.1700
Data Index: 4861878 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.7536. Min Act: -0.1700
Data Index: 4335459 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6599. Min Range: -7.6599
Max Act: 6.7536. Min Act: -0.1700
Data Index: 8279934 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19