Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0154. Min Range: -5.0154
Max Act: 5.0154. Min Act: -0.1700
Data Index: 2455567 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.7029. Min Act: -0.1700
Data Index: 2455579 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.7654. Min Act: -0.1700
Data Index: 7405148 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.6404. Min Act: -0.1700
Data Index: 8115223 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.4842. Min Act: -0.1700
Data Index: 4102474 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.4217. Min Act: -0.1700
Data Index: 2455577 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.3279. Min Act: -0.1700
Data Index: 2455575 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.3904. Min Act: -0.1700
Data Index: 2455578 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.3904. Min Act: -0.1700
Data Index: 4897707 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.3279. Min Act: -0.1700
Data Index: 2455583 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.3279. Min Act: -0.1700
Data Index: 5644251 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.2654. Min Act: -0.1700
Data Index: 2455571 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.2966. Min Act: -0.1700
Data Index: 2455566 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.3591. Min Act: -0.1700
Data Index: 5341108 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.2966. Min Act: -0.1700
Data Index: 1701414 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.2966. Min Act: -0.1700
Data Index: 2455574 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.3591. Min Act: -0.1700
Data Index: 2455572 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.2654. Min Act: -0.1700
Data Index: 2455563 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.2654. Min Act: -0.1700
Data Index: 2455581 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.2654. Min Act: -0.1700
Data Index: 2455580 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19