Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3219 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.3925. Min Act: -0.1700
Data Index: 7221946 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.2675. Min Act: -0.1700
Data Index: 7437517 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.0800. Min Act: -0.1700
Data Index: 2034873 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.0487. Min Act: -0.1700
Data Index: 3320318 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.0175. Min Act: -0.1700
Data Index: 6411195 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9550. Min Act: -0.1700
Data Index: 7553747 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9862. Min Act: -0.1700
Data Index: 3252257 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9862. Min Act: -0.1700
Data Index: 8688274 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9550. Min Act: -0.1700
Data Index: 5301882 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9237. Min Act: -0.1700
Data Index: 3040465 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9862. Min Act: -0.1700
Data Index: 2807770 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9550. Min Act: -0.1700
Data Index: 5124468 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9237. Min Act: -0.1700
Data Index: 2145655 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.8925. Min Act: -0.1700
Data Index: 4794978 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.8925. Min Act: -0.1700
Data Index: 1939896 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.8300. Min Act: -0.1700
Data Index: 4038634 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.8300. Min Act: -0.1700
Data Index: 7895259 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.8612. Min Act: -0.1700
Data Index: 7306187 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.8612. Min Act: -0.1700
Data Index: 5678423 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.8612. Min Act: -0.1700
Data Index: 3323878 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19