Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2857 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.1944. Min Act: -0.1700
Data Index: 666518 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.1006. Min Act: -0.1700
Data Index: 4454107 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.1631. Min Act: -0.1700
Data Index: 3334141 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.1006. Min Act: -0.1700
Data Index: 5440782 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.0381. Min Act: -0.1700
Data Index: 2597376 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.1006. Min Act: -0.1700
Data Index: 2994122 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.1006. Min Act: -0.1700
Data Index: 4040391 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.0069. Min Act: -0.1700
Data Index: 373633 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.0694. Min Act: -0.1700
Data Index: 561969 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.0069. Min Act: -0.1700
Data Index: 5201159 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.0069. Min Act: -0.1700
Data Index: 5465350 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.0069. Min Act: -0.1700
Data Index: 7715728 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1944. Min Range: -5.1944
Max Act: 4.9756. Min Act: -0.1700
Data Index: 684552 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1944. Min Range: -5.1944
Max Act: 4.9756. Min Act: -0.1700
Data Index: 5834928 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1944. Min Range: -5.1944
Max Act: 4.9444. Min Act: -0.1700
Data Index: 1591090 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1944. Min Range: -5.1944
Max Act: 4.9444. Min Act: -0.1700
Data Index: 3893438 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1944. Min Range: -5.1944
Max Act: 5.0069. Min Act: -0.1700
Data Index: 8096162 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1944. Min Range: -5.1944
Max Act: 4.9131. Min Act: -0.1700
Data Index: 6551817 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1944. Min Range: -5.1944
Max Act: 4.9444. Min Act: -0.1700
Data Index: 7195880 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1944. Min Range: -5.1944
Max Act: 4.9444. Min Act: -0.1700
Data Index: 5486089 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19