Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3187 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3962. Min Range: -7.3962
Max Act: 7.3962. Min Act: -0.1700
Data Index: 4457757 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3962. Min Range: -7.3962
Max Act: 7.0525. Min Act: -0.1700
Data Index: 7198271 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.6462. Min Act: -0.1700
Data Index: 7215831 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.5837. Min Act: -0.1700
Data Index: 5400781 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.5837. Min Act: -0.1700
Data Index: 1620452 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.5525. Min Act: -0.1700
Data Index: 7031968 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.4900. Min Act: -0.1700
Data Index: 682440 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.4587. Min Act: -0.1700
Data Index: 7386172 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.4275. Min Act: -0.1700
Data Index: 4262351 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.4275. Min Act: -0.1700
Data Index: 6140798 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.4587. Min Act: -0.1700
Data Index: 8620843 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.3962. Min Act: -0.1700
Data Index: 5888092 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.3962. Min Act: -0.1700
Data Index: 5422113 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.3650. Min Act: -0.1700
Data Index: 4483812 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.3337. Min Act: -0.1700
Data Index: 1612701 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.3337. Min Act: -0.1700
Data Index: 1582864 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.3650. Min Act: -0.1700
Data Index: 5836802 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.3650. Min Act: -0.1700
Data Index: 8515366 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.3025. Min Act: -0.1700
Data Index: 4543955 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3962. Min Range: -7.3962
Max Act: 6.3025. Min Act: -0.1700
Data Index: 801487 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19