Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5542 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4062. Min Range: -7.4062
Max Act: 7.4062. Min Act: -0.1700
Data Index: 670549 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.8437. Min Act: -0.1700
Data Index: 5642989 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.7187. Min Act: -0.1700
Data Index: 6164228 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.6249. Min Act: -0.1700
Data Index: 3021317 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.6249. Min Act: -0.1700
Data Index: 2360889 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.6562. Min Act: -0.1700
Data Index: 8594826 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.5937. Min Act: -0.1700
Data Index: 7360352 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.4374. Min Act: -0.1700
Data Index: 2627446 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.4062. Min Act: -0.1700
Data Index: 1203718 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.3749. Min Act: -0.1700
Data Index: 7484303 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.3749. Min Act: -0.1700
Data Index: 3318438 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.3749. Min Act: -0.1700
Data Index: 7122635 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.3437. Min Act: -0.1700
Data Index: 4556424 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.3124. Min Act: -0.1700
Data Index: 5634068 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.3437. Min Act: -0.1700
Data Index: 548662 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.3124. Min Act: -0.1700
Data Index: 5730517 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.2812. Min Act: -0.1700
Data Index: 354411 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.2499. Min Act: -0.1700
Data Index: 2796893 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.2812. Min Act: -0.1700
Data Index: 5442981 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4062. Min Range: -7.4062
Max Act: 6.2187. Min Act: -0.1700
Data Index: 7500259 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19