Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2834 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0724. Min Range: -5.0724
Max Act: 5.0724. Min Act: -0.1700
Data Index: 2539752 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.8849. Min Act: -0.1700
Data Index: 7424343 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.9161. Min Act: -0.1700
Data Index: 4506179 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.8536. Min Act: -0.1700
Data Index: 4134047 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.8224. Min Act: -0.1700
Data Index: 1978960 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.8536. Min Act: -0.1700
Data Index: 8382286 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.8536. Min Act: -0.1700
Data Index: 3759077 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.8224. Min Act: -0.1700
Data Index: 8506768 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.8224. Min Act: -0.1700
Data Index: 6027903 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.7599. Min Act: -0.1700
Data Index: 1002982 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.8224. Min Act: -0.1700
Data Index: 7944457 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.8224. Min Act: -0.1700
Data Index: 1623902 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.7911. Min Act: -0.1700
Data Index: 3759080 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.7911. Min Act: -0.1700
Data Index: 6979933 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.8224. Min Act: -0.1700
Data Index: 6707437 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.7911. Min Act: -0.1700
Data Index: 6520383 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.7911. Min Act: -0.1700
Data Index: 57298 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.7911. Min Act: -0.1700
Data Index: 5362241 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.7599. Min Act: -0.1700
Data Index: 391666 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0724. Min Range: -5.0724
Max Act: 4.7599. Min Act: -0.1700
Data Index: 515933 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19