Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4624 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2092. Min Range: -7.2092
Max Act: 7.2092. Min Act: -0.1700
Data Index: 8234946 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2092. Min Range: -7.2092
Max Act: 7.0529. Min Act: -0.1700
Data Index: 8767187 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.8967. Min Act: -0.1700
Data Index: 5519709 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.8654. Min Act: -0.1700
Data Index: 1790441 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.8029. Min Act: -0.1700
Data Index: 5325241 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.8029. Min Act: -0.1700
Data Index: 1058795 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7717. Min Act: -0.1700
Data Index: 1058796 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.8029. Min Act: -0.1700
Data Index: 4515531 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7717. Min Act: -0.1700
Data Index: 512349 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7717. Min Act: -0.1700
Data Index: 4771561 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7404. Min Act: -0.1700
Data Index: 8748851 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7404. Min Act: -0.1700
Data Index: 3596301 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7404. Min Act: -0.1700
Data Index: 932070 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7404. Min Act: -0.1700
Data Index: 3378202 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7404. Min Act: -0.1700
Data Index: 1790444 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7092. Min Act: -0.1700
Data Index: 2708422 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7404. Min Act: -0.1700
Data Index: 4822137 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7404. Min Act: -0.1700
Data Index: 7868152 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7404. Min Act: -0.1700
Data Index: 860535 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2092. Min Range: -7.2092
Max Act: 6.7092. Min Act: -0.1700
Data Index: 4479089 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19