Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 388 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1105. Min Range: -6.1105
Max Act: 6.1105. Min Act: -0.1700
Data Index: 3139554 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1105. Min Range: -6.1105
Max Act: 6.0167. Min Act: -0.1700
Data Index: 5798963 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1105. Min Range: -6.1105
Max Act: 6.0167. Min Act: -0.1700
Data Index: 8481360 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.9855. Min Act: -0.1700
Data Index: 7736196 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.9542. Min Act: -0.1700
Data Index: 3552795 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.9542. Min Act: -0.1700
Data Index: 2837 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.9230. Min Act: -0.1700
Data Index: 4944543 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.8917. Min Act: -0.1700
Data Index: 4994396 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.9230. Min Act: -0.1700
Data Index: 976408 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.9230. Min Act: -0.1700
Data Index: 1045142 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.9230. Min Act: -0.1700
Data Index: 5604150 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.9230. Min Act: -0.1700
Data Index: 7720341 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.9230. Min Act: -0.1700
Data Index: 5028349 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.8917. Min Act: -0.1700
Data Index: 6151428 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.8917. Min Act: -0.1700
Data Index: 3321963 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.8917. Min Act: -0.1700
Data Index: 6904044 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.8917. Min Act: -0.1700
Data Index: 5925884 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.9230. Min Act: -0.1700
Data Index: 4205373 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.8917. Min Act: -0.1700
Data Index: 1697581 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1105. Min Range: -6.1105
Max Act: 5.8605. Min Act: -0.1700
Data Index: 135081 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19