Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.7599. Min Act: -0.1700
Data Index: 7187217 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.7599. Min Act: -0.1700
Data Index: 1834451 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.7599. Min Act: -0.1700
Data Index: 5853684 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.7287. Min Act: -0.1700
Data Index: 8394784 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6974. Min Act: -0.1700
Data Index: 8317257 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6662. Min Act: -0.1700
Data Index: 5181697 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6974. Min Act: -0.1700
Data Index: 5484651 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6662. Min Act: -0.1700
Data Index: 103958 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6662. Min Act: -0.1700
Data Index: 1258866 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6349. Min Act: -0.1700
Data Index: 6907936 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6349. Min Act: -0.1700
Data Index: 3671491 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6349. Min Act: -0.1700
Data Index: 1302760 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6349. Min Act: -0.1700
Data Index: 6268320 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6349. Min Act: -0.1700
Data Index: 4308504 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6037. Min Act: -0.1700
Data Index: 870031 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6037. Min Act: -0.1700
Data Index: 6495288 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6349. Min Act: -0.1700
Data Index: 4001410 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6037. Min Act: -0.1700
Data Index: 3996797 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6037. Min Act: -0.1699
Data Index: 8374324 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7599. Min Range: -5.7599
Max Act: 5.6037. Min Act: -0.1700
Data Index: 64265 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19