Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.7960. Min Act: -0.1700
Data Index: 1884961 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.7022. Min Act: -0.1700
Data Index: 340434 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.6397. Min Act: -0.1700
Data Index: 1773875 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.4835. Min Act: -0.1700
Data Index: 1228802 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.4835. Min Act: -0.1700
Data Index: 3704120 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.4210. Min Act: -0.1700
Data Index: 7385961 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.4210. Min Act: -0.1700
Data Index: 4639159 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.3585. Min Act: -0.1700
Data Index: 4613367 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.3272. Min Act: -0.1700
Data Index: 4962664 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.2022. Min Act: -0.1700
Data Index: 972178 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.2335. Min Act: -0.1700
Data Index: 3814634 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.2647. Min Act: -0.1700
Data Index: 199356 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.2335. Min Act: -0.1700
Data Index: 1581400 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.2335. Min Act: -0.1700
Data Index: 2458282 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.2022. Min Act: -0.1700
Data Index: 7840407 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.2022. Min Act: -0.1700
Data Index: 79441 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.2022. Min Act: -0.1700
Data Index: 2472224 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.1397. Min Act: -0.1700
Data Index: 4890919 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.1397. Min Act: -0.1700
Data Index: 5213119 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7960. Min Range: -5.7960
Max Act: 5.1397. Min Act: -0.1700
Data Index: 5512548 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19