Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3680 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0135. Min Range: -4.0135
Max Act: 4.0135. Min Act: -0.1700
Data Index: 4132590 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.8416. Min Act: -0.1700
Data Index: 6207989 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.7790. Min Act: -0.1700
Data Index: 8347050 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.6696. Min Act: -0.1700
Data Index: 6440378 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.6383. Min Act: -0.1700
Data Index: 2048344 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.6070. Min Act: -0.1700
Data Index: 1369641 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.6383. Min Act: -0.1700
Data Index: 6268024 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.6226. Min Act: -0.1700
Data Index: 1847281 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.5443. Min Act: -0.1700
Data Index: 2630352 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.5600. Min Act: -0.1700
Data Index: 1104154 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.5600. Min Act: -0.1700
Data Index: 5709710 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.5287. Min Act: -0.1700
Data Index: 3888460 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.5287. Min Act: -0.1700
Data Index: 6268025 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.5287. Min Act: -0.1700
Data Index: 4236303 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.5287. Min Act: -0.1700
Data Index: 2780476 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.4974. Min Act: -0.1700
Data Index: 2333212 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.5130. Min Act: -0.1700
Data Index: 7567386 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.4974. Min Act: -0.1700
Data Index: 253696 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.4974. Min Act: -0.1700
Data Index: 5851104 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0135. Min Range: -4.0135
Max Act: 3.4974. Min Act: -0.1700
Data Index: 5972411 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19