Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3904. Min Range: -4.3904
Max Act: 4.3904. Min Act: -0.1700
Data Index: 879608 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3904. Min Range: -4.3904
Max Act: 4.2341. Min Act: -0.1700
Data Index: 7816873 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3904. Min Range: -4.3904
Max Act: 4.1091. Min Act: -0.1700
Data Index: 613344 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3904. Min Range: -4.3904
Max Act: 4.0153. Min Act: -0.1700
Data Index: 6529691 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3904. Min Range: -4.3904
Max Act: 4.0153. Min Act: -0.1700
Data Index: 8808493 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.9841. Min Act: -0.1700
Data Index: 4548127 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.9841. Min Act: -0.1700
Data Index: 8582420 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.9215. Min Act: -0.1700
Data Index: 4786247 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.8903. Min Act: -0.1700
Data Index: 3629955 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.8277. Min Act: -0.1700
Data Index: 6448974 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.8277. Min Act: -0.1700
Data Index: 6311617 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.8277. Min Act: -0.1700
Data Index: 8321181 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.8277. Min Act: -0.1700
Data Index: 3407775 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.7965. Min Act: -0.1700
Data Index: 6296978 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.7652. Min Act: -0.1700
Data Index: 6607178 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.7652. Min Act: -0.1700
Data Index: 5469994 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.7026. Min Act: -0.1700
Data Index: 7262582 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.7339. Min Act: -0.1700
Data Index: 3293304 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.7339. Min Act: -0.1700
Data Index: 7114267 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3904. Min Range: -4.3904
Max Act: 3.7652. Min Act: -0.1700
Data Index: 6894991 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19