Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4546 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2142. Min Range: -7.2142
Max Act: 7.2142. Min Act: -0.1700
Data Index: 4309699 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2142. Min Range: -7.2142
Max Act: 7.0267. Min Act: -0.1700
Data Index: 11256 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2142. Min Range: -7.2142
Max Act: 7.0267. Min Act: -0.1700
Data Index: 1371957 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.9329. Min Act: -0.1700
Data Index: 2355239 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.9017. Min Act: -0.1700
Data Index: 5091361 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.8079. Min Act: -0.1700
Data Index: 938056 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.8079. Min Act: -0.1700
Data Index: 1104567 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.8079. Min Act: -0.1700
Data Index: 6179253 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.7142. Min Act: -0.1700
Data Index: 6155929 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.7767. Min Act: -0.1700
Data Index: 1504580 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.7767. Min Act: -0.1700
Data Index: 4998224 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.7142. Min Act: -0.1700
Data Index: 173546 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.7142. Min Act: -0.1700
Data Index: 7652777 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.7454. Min Act: -0.1700
Data Index: 3197345 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.7142. Min Act: -0.1700
Data Index: 5061751 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.6829. Min Act: -0.1700
Data Index: 4223934 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.6829. Min Act: -0.1700
Data Index: 5435262 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.6517. Min Act: -0.1700
Data Index: 3476220 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.5892. Min Act: -0.1700
Data Index: 7387499 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2142. Min Range: -7.2142
Max Act: 6.5892. Min Act: -0.1700
Data Index: 6078928 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19