Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.6600. Min Act: -0.1700
Data Index: 40692 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.5975. Min Act: -0.1700
Data Index: 600565 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.4100. Min Act: -0.1700
Data Index: 6987364 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.3788. Min Act: -0.1700
Data Index: 2914061 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.3475. Min Act: -0.1700
Data Index: 5330279 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.3475. Min Act: -0.1700
Data Index: 3648772 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.3788. Min Act: -0.1700
Data Index: 3912567 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.3475. Min Act: -0.1700
Data Index: 1836338 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.3475. Min Act: -0.1700
Data Index: 3975855 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.3163. Min Act: -0.1700
Data Index: 3878068 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.3163. Min Act: -0.1700
Data Index: 7826257 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.2538. Min Act: -0.1700
Data Index: 5493530 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.2538. Min Act: -0.1700
Data Index: 184746 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.2538. Min Act: -0.1700
Data Index: 1724828 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.2538. Min Act: -0.1700
Data Index: 5914151 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.2225. Min Act: -0.1700
Data Index: 6849791 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.2225. Min Act: -0.1700
Data Index: 5591782 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.2225. Min Act: -0.1700
Data Index: 1497574 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.2225. Min Act: -0.1700
Data Index: 691046 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6600. Min Range: -5.6600
Max Act: 5.1913. Min Act: -0.1700
Data Index: 5944908 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19