Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.2276. Min Act: -0.1700
Data Index: 3088511 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.2119. Min Act: -0.1700
Data Index: 3197480 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.1961. Min Act: -0.1700
Data Index: 121053 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.1647. Min Act: -0.1700
Data Index: 3052608 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.1017. Min Act: -0.1700
Data Index: 6233216 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0859. Min Act: -0.1700
Data Index: 6226682 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0859. Min Act: -0.1700
Data Index: 3718932 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0859. Min Act: -0.1700
Data Index: 3825088 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0859. Min Act: -0.1700
Data Index: 801710 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0859. Min Act: -0.1700
Data Index: 8366822 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0701. Min Act: -0.1700
Data Index: 4945291 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0701. Min Act: -0.1700
Data Index: 4942761 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0701. Min Act: -0.1700
Data Index: 8127969 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0386. Min Act: -0.1700
Data Index: 1380506 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0544. Min Act: -0.1700
Data Index: 4718800 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0386. Min Act: -0.1700
Data Index: 2728831 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0386. Min Act: -0.1700
Data Index: 2395622 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0386. Min Act: -0.1700
Data Index: 625773 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0228. Min Act: -0.1700
Data Index: 242460 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2276. Min Range: -3.2276
Max Act: 3.0228. Min Act: -0.1700
Data Index: 3462172 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19