Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2618 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0544. Min Range: -7.0544
Max Act: 7.0544. Min Act: -0.1700
Data Index: 405051 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0544. Min Range: -7.0544
Max Act: 7.0232. Min Act: -0.1700
Data Index: 3136535 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.8982. Min Act: -0.1700
Data Index: 24175 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.8357. Min Act: -0.1700
Data Index: 6892894 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.8357. Min Act: -0.1700
Data Index: 2692082 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.8357. Min Act: -0.1700
Data Index: 43545 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.7732. Min Act: -0.1700
Data Index: 6952022 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.7419. Min Act: -0.1700
Data Index: 6776541 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.7419. Min Act: -0.1700
Data Index: 4749281 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.7107. Min Act: -0.1700
Data Index: 3600724 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.6794. Min Act: -0.1700
Data Index: 2157971 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.6482. Min Act: -0.1700
Data Index: 2535062 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.6482. Min Act: -0.1700
Data Index: 4866602 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.6482. Min Act: -0.1700
Data Index: 5998449 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.6482. Min Act: -0.1700
Data Index: 2446119 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.6482. Min Act: -0.1700
Data Index: 486843 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.6482. Min Act: -0.1700
Data Index: 7935546 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.6169. Min Act: -0.1700
Data Index: 2799294 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.6482. Min Act: -0.1700
Data Index: 552467 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0544. Min Range: -7.0544
Max Act: 6.6169. Min Act: -0.1700
Data Index: 3234906 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19