Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 846 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1181. Min Range: -3.1181
Max Act: 3.1181. Min Act: -0.1700
Data Index: 6165811 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1181. Min Range: -3.1181
Max Act: 3.0866. Min Act: -0.1700
Data Index: 7704918 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1181. Min Range: -3.1181
Max Act: 3.0392. Min Act: -0.1700
Data Index: 8027992 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1181. Min Range: -3.1181
Max Act: 3.0392. Min Act: -0.1700
Data Index: 5871596 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1181. Min Range: -3.1181
Max Act: 3.0235. Min Act: -0.1700
Data Index: 2366181 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1181. Min Range: -3.1181
Max Act: 3.0077. Min Act: -0.1700
Data Index: 495304 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1181. Min Range: -3.1181
Max Act: 3.0077. Min Act: -0.1700
Data Index: 3885245 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1181. Min Range: -3.1181
Max Act: 3.0077. Min Act: -0.1700
Data Index: 211526 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1181. Min Range: -3.1181
Max Act: 3.0392. Min Act: -0.1700
Data Index: 495305 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1181. Min Range: -3.1181
Max Act: 2.9760. Min Act: -0.1700
Data Index: 6848093 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1181. Min Range: -3.1181
Max Act: 2.9444. Min Act: -0.1700
Data Index: 4466410 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1181. Min Range: -3.1181
Max Act: 2.9760. Min Act: -0.1700
Data Index: 3234699 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1181. Min Range: -3.1181
Max Act: 2.9127. Min Act: -0.1700
Data Index: 6565873 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1181. Min Range: -3.1181
Max Act: 2.9444. Min Act: -0.1700
Data Index: 186590 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1181. Min Range: -3.1181
Max Act: 2.9444. Min Act: -0.1700
Data Index: 838834 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1181. Min Range: -3.1181
Max Act: 2.8810. Min Act: -0.1700
Data Index: 6808520 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1181. Min Range: -3.1181
Max Act: 2.8810. Min Act: -0.1700
Data Index: 3561466 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1181. Min Range: -3.1181
Max Act: 2.8810. Min Act: -0.1700
Data Index: 4668935 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1181. Min Range: -3.1181
Max Act: 2.8810. Min Act: -0.1700
Data Index: 4078179 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1181. Min Range: -3.1181
Max Act: 2.8810. Min Act: -0.1700
Data Index: 4668941 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19