Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1787 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4570. Min Range: -5.4570
Max Act: 5.4570. Min Act: -0.1700
Data Index: 8628711 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4570. Min Range: -5.4570
Max Act: 5.4257. Min Act: -0.1700
Data Index: 5388336 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4570. Min Range: -5.4570
Max Act: 5.3007. Min Act: -0.1700
Data Index: 262473 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4570. Min Range: -5.4570
Max Act: 5.2382. Min Act: -0.1700
Data Index: 682904 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4570. Min Range: -5.4570
Max Act: 5.2382. Min Act: -0.1700
Data Index: 582247 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4570. Min Range: -5.4570
Max Act: 5.2070. Min Act: -0.1700
Data Index: 2833639 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4570. Min Range: -5.4570
Max Act: 5.1757. Min Act: -0.1700
Data Index: 6411240 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4570. Min Range: -5.4570
Max Act: 5.2070. Min Act: -0.1700
Data Index: 2923139 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4570. Min Range: -5.4570
Max Act: 5.1132. Min Act: -0.1700
Data Index: 4825954 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4570. Min Range: -5.4570
Max Act: 5.1132. Min Act: -0.1700
Data Index: 3173115 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4570. Min Range: -5.4570
Max Act: 5.0195. Min Act: -0.1700
Data Index: 47641 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4570. Min Range: -5.4570
Max Act: 4.9882. Min Act: -0.1700
Data Index: 7537435 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4570. Min Range: -5.4570
Max Act: 5.0195. Min Act: -0.1700
Data Index: 5096503 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4570. Min Range: -5.4570
Max Act: 4.9570. Min Act: -0.1700
Data Index: 2947493 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4570. Min Range: -5.4570
Max Act: 4.9882. Min Act: -0.1700
Data Index: 4805478 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4570. Min Range: -5.4570
Max Act: 4.9257. Min Act: -0.1700
Data Index: 2476161 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4570. Min Range: -5.4570
Max Act: 4.9257. Min Act: -0.1700
Data Index: 6538353 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4570. Min Range: -5.4570
Max Act: 4.9570. Min Act: -0.1700
Data Index: 2927938 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4570. Min Range: -5.4570
Max Act: 4.8945. Min Act: -0.1700
Data Index: 2771159 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4570. Min Range: -5.4570
Max Act: 4.8632. Min Act: -0.1700
Data Index: 4676500 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19