Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5793 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0093. Min Range: -5.0093
Max Act: 5.0093. Min Act: -0.1700
Data Index: 8032554 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.9781. Min Act: -0.1699
Data Index: 3625142 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.8843. Min Act: -0.1700
Data Index: 5829812 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.8531. Min Act: -0.1700
Data Index: 1062570 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.8218. Min Act: -0.1700
Data Index: 1353965 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.8218. Min Act: -0.1700
Data Index: 5246228 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.8218. Min Act: -0.1699
Data Index: 4396712 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7906. Min Act: -0.1700
Data Index: 4870197 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7906. Min Act: -0.1700
Data Index: 2197458 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7593. Min Act: -0.1700
Data Index: 1855853 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7593. Min Act: -0.1700
Data Index: 1155831 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7593. Min Act: -0.1700
Data Index: 6902184 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7593. Min Act: -0.1700
Data Index: 82723 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7281. Min Act: -0.1700
Data Index: 8126284 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7593. Min Act: -0.1700
Data Index: 3563118 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7281. Min Act: -0.1700
Data Index: 1498591 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7593. Min Act: -0.1700
Data Index: 2766807 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.7281. Min Act: -0.1700
Data Index: 3204460 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.6968. Min Act: -0.1700
Data Index: 777086 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0093. Min Range: -5.0093
Max Act: 4.6968. Min Act: -0.1700
Data Index: 2595636 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19