Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0305. Min Range: -5.0305
Max Act: 5.0305. Min Act: -0.1700
Data Index: 6489979 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9993. Min Act: -0.1700
Data Index: 5318461 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9993. Min Act: -0.1700
Data Index: 6379056 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9993. Min Act: -0.1700
Data Index: 8092703 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0305. Min Range: -5.0305
Max Act: 5.0305. Min Act: -0.1700
Data Index: 4555499 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9993. Min Act: -0.1700
Data Index: 4490578 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9993. Min Act: -0.1700
Data Index: 8092704 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9993. Min Act: -0.1700
Data Index: 1207272 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9680. Min Act: -0.1700
Data Index: 7522783 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9993. Min Act: -0.1700
Data Index: 7719326 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9680. Min Act: -0.1700
Data Index: 8498178 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9680. Min Act: -0.1700
Data Index: 8252241 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9680. Min Act: -0.1700
Data Index: 5002150 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9680. Min Act: -0.1700
Data Index: 7343248 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9368. Min Act: -0.1700
Data Index: 4026725 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9368. Min Act: -0.1700
Data Index: 3970268 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9368. Min Act: -0.1700
Data Index: 3323101 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9055. Min Act: -0.1700
Data Index: 204622 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9680. Min Act: -0.1699
Data Index: 681148 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0305. Min Range: -5.0305
Max Act: 4.9368. Min Act: -0.1700
Data Index: 2897238 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19