Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0330. Min Range: -5.0330
Max Act: 5.0330. Min Act: -0.1700
Data Index: 3465755 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0330. Min Range: -5.0330
Max Act: 5.0330. Min Act: -0.1700
Data Index: 7780888 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.9392. Min Act: -0.1700
Data Index: 2814081 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.9080. Min Act: -0.1700
Data Index: 4861369 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.9080. Min Act: -0.1700
Data Index: 8613119 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.8142. Min Act: -0.1700
Data Index: 7593600 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.8767. Min Act: -0.1700
Data Index: 3252894 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.9080. Min Act: -0.1700
Data Index: 4342408 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.8455. Min Act: -0.1700
Data Index: 3653070 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.8455. Min Act: -0.1700
Data Index: 2721911 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.7517. Min Act: -0.1700
Data Index: 1990656 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.7517. Min Act: -0.1700
Data Index: 4140955 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.7830. Min Act: -0.1700
Data Index: 6795581 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.7830. Min Act: -0.1700
Data Index: 7962610 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.7830. Min Act: -0.1700
Data Index: 7634910 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.6892. Min Act: -0.1700
Data Index: 7135558 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.7830. Min Act: -0.1700
Data Index: 2987527 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.7830. Min Act: -0.1700
Data Index: 775572 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.7830. Min Act: -0.1700
Data Index: 200967 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0330. Min Range: -5.0330
Max Act: 4.8142. Min Act: -0.1700
Data Index: 1310385 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19