Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5898 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2683. Min Range: -6.2683
Max Act: 6.2683. Min Act: -0.1700
Data Index: 1621087 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2683. Min Range: -6.2683
Max Act: 6.1120. Min Act: -0.1700
Data Index: 1302252 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2683. Min Range: -6.2683
Max Act: 6.0808. Min Act: -0.1700
Data Index: 6938532 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2683. Min Range: -6.2683
Max Act: 6.1120. Min Act: -0.1700
Data Index: 7118311 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2683. Min Range: -6.2683
Max Act: 6.0808. Min Act: -0.1700
Data Index: 6489683 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2683. Min Range: -6.2683
Max Act: 6.0495. Min Act: -0.1700
Data Index: 2010831 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2683. Min Range: -6.2683
Max Act: 6.0495. Min Act: -0.1700
Data Index: 6495286 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2683. Min Range: -6.2683
Max Act: 6.0495. Min Act: -0.1700
Data Index: 2418692 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2683. Min Range: -6.2683
Max Act: 6.0495. Min Act: -0.1700
Data Index: 764572 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2683. Min Range: -6.2683
Max Act: 6.0495. Min Act: -0.1700
Data Index: 8076654 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2683. Min Range: -6.2683
Max Act: 6.0183. Min Act: -0.1700
Data Index: 2414514 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2683. Min Range: -6.2683
Max Act: 6.0183. Min Act: -0.1700
Data Index: 7289591 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2683. Min Range: -6.2683
Max Act: 5.9870. Min Act: -0.1700
Data Index: 6489686 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2683. Min Range: -6.2683
Max Act: 5.9870. Min Act: -0.1700
Data Index: 7387830 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2683. Min Range: -6.2683
Max Act: 5.9558. Min Act: -0.1700
Data Index: 3283675 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2683. Min Range: -6.2683
Max Act: 5.9558. Min Act: -0.1700
Data Index: 8399529 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2683. Min Range: -6.2683
Max Act: 5.9870. Min Act: -0.1700
Data Index: 7306445 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2683. Min Range: -6.2683
Max Act: 5.8933. Min Act: -0.1700
Data Index: 4672276 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2683. Min Range: -6.2683
Max Act: 5.9245. Min Act: -0.1700
Data Index: 4140723 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2683. Min Range: -6.2683
Max Act: 5.9245. Min Act: -0.1700
Data Index: 4262951 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19