Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2545 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.2934. Min Act: -0.1700
Data Index: 7315807 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.2622. Min Act: -0.1700
Data Index: 8309595 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.1684. Min Act: -0.1700
Data Index: 7228323 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.1684. Min Act: -0.1700
Data Index: 8639380 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.1059. Min Act: -0.1700
Data Index: 5263389 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.1059. Min Act: -0.1700
Data Index: 8619634 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0747. Min Act: -0.1700
Data Index: 7973478 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0747. Min Act: -0.1700
Data Index: 3729410 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0434. Min Act: -0.1700
Data Index: 7243930 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0434. Min Act: -0.1700
Data Index: 7915793 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0434. Min Act: -0.1700
Data Index: 8558307 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0434. Min Act: -0.1700
Data Index: 4800901 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0434. Min Act: -0.1700
Data Index: 3817656 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0122. Min Act: -0.1700
Data Index: 4098584 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0122. Min Act: -0.1700
Data Index: 942029 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0122. Min Act: -0.1700
Data Index: 8267440 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0122. Min Act: -0.1700
Data Index: 3118479 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0122. Min Act: -0.1700
Data Index: 6280226 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.9809. Min Act: -0.1700
Data Index: 1217141 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.9809. Min Act: -0.1700
Data Index: 2619890 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19