Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6306 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.5956. Min Act: -0.1700
Data Index: 7545346 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.4706. Min Act: -0.1700
Data Index: 4131179 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.3768. Min Act: -0.1700
Data Index: 2134577 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.3456. Min Act: -0.1700
Data Index: 5482222 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.2831. Min Act: -0.1700
Data Index: 5656178 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.2831. Min Act: -0.1700
Data Index: 7763256 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.2831. Min Act: -0.1700
Data Index: 2869097 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.2206. Min Act: -0.1700
Data Index: 4341865 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.1893. Min Act: -0.1700
Data Index: 1563374 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.1893. Min Act: -0.1700
Data Index: 7989328 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.1581. Min Act: -0.1700
Data Index: 7189263 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.1581. Min Act: -0.1700
Data Index: 1003414 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.1581. Min Act: -0.1700
Data Index: 6319167 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.1268. Min Act: -0.1700
Data Index: 4940821 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.1268. Min Act: -0.1700
Data Index: 4440673 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.0956. Min Act: -0.1700
Data Index: 3310011 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.0956. Min Act: -0.1700
Data Index: 3236015 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.0643. Min Act: -0.1700
Data Index: 7305121 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.0643. Min Act: -0.1700
Data Index: 2701896 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.0331. Min Act: -0.1700
Data Index: 5624688 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19