Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4600 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1416. Min Range: -7.1416
Max Act: 7.1416. Min Act: -0.1700
Data Index: 511216 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1416. Min Range: -7.1416
Max Act: 7.0166. Min Act: -0.1700
Data Index: 4530089 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.7041. Min Act: -0.1700
Data Index: 8763450 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.6729. Min Act: -0.1700
Data Index: 6284611 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.6729. Min Act: -0.1700
Data Index: 450122 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.6729. Min Act: -0.1700
Data Index: 7420790 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.6729. Min Act: -0.1700
Data Index: 6866529 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.6416. Min Act: -0.1700
Data Index: 1865945 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.6416. Min Act: -0.1700
Data Index: 2397285 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.6416. Min Act: -0.1700
Data Index: 3389224 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.6104. Min Act: -0.1700
Data Index: 3130081 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.6104. Min Act: -0.1700
Data Index: 2914238 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.5166. Min Act: -0.1700
Data Index: 3065787 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.5166. Min Act: -0.1700
Data Index: 4231744 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.5166. Min Act: -0.1700
Data Index: 8103246 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.5166. Min Act: -0.1700
Data Index: 5003545 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.4229. Min Act: -0.1700
Data Index: 8420860 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.4229. Min Act: -0.1700
Data Index: 769222 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.4229. Min Act: -0.1700
Data Index: 493808 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1416. Min Range: -7.1416
Max Act: 6.3916. Min Act: -0.1700
Data Index: 1719509 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19