Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1238 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.4049. Min Act: -0.1700
Data Index: 1697815 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.4362. Min Act: -0.1700
Data Index: 1458901 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.4049. Min Act: -0.1700
Data Index: 6273204 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.3737. Min Act: -0.1700
Data Index: 1272066 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.3737. Min Act: -0.1700
Data Index: 4293540 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.3737. Min Act: -0.1700
Data Index: 3294003 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.3424. Min Act: -0.1700
Data Index: 3434154 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.3424. Min Act: -0.1700
Data Index: 1998890 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.3424. Min Act: -0.1700
Data Index: 3101741 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.3112. Min Act: -0.1700
Data Index: 5288544 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.3112. Min Act: -0.1700
Data Index: 5627029 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.3112. Min Act: -0.1700
Data Index: 28226 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.3112. Min Act: -0.1700
Data Index: 5288548 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.3112. Min Act: -0.1700
Data Index: 6856190 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.3112. Min Act: -0.1700
Data Index: 82029 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.2799. Min Act: -0.1700
Data Index: 5589386 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.2799. Min Act: -0.1700
Data Index: 7578972 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.2799. Min Act: -0.1700
Data Index: 2785884 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.2799. Min Act: -0.1700
Data Index: 6249123 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4362. Min Range: -4.4362
Max Act: 4.2799. Min Act: -0.1700
Data Index: 2397889 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19