Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0668. Min Range: -5.0668
Max Act: 5.0668. Min Act: -0.1700
Data Index: 8177179 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0668. Min Range: -5.0668
Max Act: 5.0668. Min Act: -0.1700
Data Index: 914898 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.9418. Min Act: -0.1700
Data Index: 2339050 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.8168. Min Act: -0.1700
Data Index: 7823693 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.7543. Min Act: -0.1700
Data Index: 498167 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.6605. Min Act: -0.1700
Data Index: 1166287 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.6605. Min Act: -0.1700
Data Index: 4439620 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.6605. Min Act: -0.1700
Data Index: 6569167 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.5980. Min Act: -0.1700
Data Index: 3180432 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.5980. Min Act: -0.1700
Data Index: 5605930 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.5980. Min Act: -0.1700
Data Index: 367210 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.4730. Min Act: -0.1700
Data Index: 219646 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.5043. Min Act: -0.1700
Data Index: 3074181 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.5043. Min Act: -0.1700
Data Index: 5570936 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.5043. Min Act: -0.1700
Data Index: 8482067 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.4730. Min Act: -0.1700
Data Index: 5741391 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.4418. Min Act: -0.1700
Data Index: 3299913 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.4730. Min Act: -0.1700
Data Index: 7353359 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.4730. Min Act: -0.1700
Data Index: 2943302 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0668. Min Range: -5.0668
Max Act: 4.4418. Min Act: -0.1700
Data Index: 5456064 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19