Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4888 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0985. Min Range: -7.0985
Max Act: 7.0985. Min Act: -0.1700
Data Index: 2679192 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.8485. Min Act: -0.1700
Data Index: 8725014 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.7860. Min Act: -0.1700
Data Index: 1677055 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.6922. Min Act: -0.1700
Data Index: 7112677 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.6922. Min Act: -0.1700
Data Index: 1937234 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.5985. Min Act: -0.1700
Data Index: 8761296 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.4422. Min Act: -0.1700
Data Index: 7693573 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.4422. Min Act: -0.1700
Data Index: 254178 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.3797. Min Act: -0.1700
Data Index: 980136 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.3172. Min Act: -0.1700
Data Index: 4844048 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.3485. Min Act: -0.1700
Data Index: 7867384 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.3485. Min Act: -0.1700
Data Index: 5328953 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.2860. Min Act: -0.1700
Data Index: 7343080 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.3172. Min Act: -0.1700
Data Index: 6003727 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.3172. Min Act: -0.1700
Data Index: 3878295 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.2547. Min Act: -0.1700
Data Index: 6477484 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.2547. Min Act: -0.1700
Data Index: 3854583 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.2547. Min Act: -0.1700
Data Index: 4966831 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.2235. Min Act: -0.1700
Data Index: 4600355 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0985. Min Range: -7.0985
Max Act: 6.2235. Min Act: -0.1700
Data Index: 4526805 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19