Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.6704. Min Act: -0.1700
Data Index: 5918742 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.6704. Min Act: -0.1700
Data Index: 138277 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.5141. Min Act: -0.1700
Data Index: 3465714 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.5141. Min Act: -0.1700
Data Index: 1546268 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.4204. Min Act: -0.1700
Data Index: 3054108 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.4204. Min Act: -0.1700
Data Index: 8827959 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.3266. Min Act: -0.1700
Data Index: 7673330 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.3266. Min Act: -0.1700
Data Index: 7496755 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.2954. Min Act: -0.1700
Data Index: 5229348 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.2641. Min Act: -0.1700
Data Index: 5933289 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.2954. Min Act: -0.1700
Data Index: 1714531 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.2641. Min Act: -0.1700
Data Index: 7040794 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.2954. Min Act: -0.1700
Data Index: 369551 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.2954. Min Act: -0.1700
Data Index: 1881099 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.2641. Min Act: -0.1700
Data Index: 129579 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.2641. Min Act: -0.1700
Data Index: 7911595 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.2641. Min Act: -0.1700
Data Index: 5887448 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.2641. Min Act: -0.1700
Data Index: 2432159 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.2329. Min Act: -0.1700
Data Index: 5684506 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6704. Min Range: -6.6704
Max Act: 6.2016. Min Act: -0.1700
Data Index: 3129753 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19