Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.8475. Min Act: -0.1700
Data Index: 5149196 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.8475. Min Act: -0.1700
Data Index: 4330272 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.8475. Min Act: -0.1700
Data Index: 2347098 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.8163. Min Act: -0.1700
Data Index: 5827570 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.8163. Min Act: -0.1700
Data Index: 7080213 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.8163. Min Act: -0.1700
Data Index: 272086 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.8163. Min Act: -0.1700
Data Index: 2832354 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.7850. Min Act: -0.1700
Data Index: 3400689 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.7850. Min Act: -0.1700
Data Index: 3313304 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.8163. Min Act: -0.1700
Data Index: 2832353 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.7537. Min Act: -0.1700
Data Index: 124813 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.7850. Min Act: -0.1700
Data Index: 342291 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.7850. Min Act: -0.1700
Data Index: 2832347 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.7850. Min Act: -0.1700
Data Index: 315408 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.7850. Min Act: -0.1700
Data Index: 2725400 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.7850. Min Act: -0.1700
Data Index: 2717603 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.7850. Min Act: -0.1700
Data Index: 2214778 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.7850. Min Act: -0.1700
Data Index: 5676 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.7850. Min Act: -0.1700
Data Index: 2156978 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8475. Min Range: -3.8475
Max Act: 3.7850. Min Act: -0.1700
Data Index: 1685062 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19