Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6072 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.4963. Min Act: -0.1700
Data Index: 7728251 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.3400. Min Act: -0.1700
Data Index: 144399 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.2150. Min Act: -0.1700
Data Index: 2095142 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.1525. Min Act: -0.1700
Data Index: 4619136 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.1525. Min Act: -0.1700
Data Index: 473116 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.1213. Min Act: -0.1700
Data Index: 3193158 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.1213. Min Act: -0.1700
Data Index: 7705079 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.1213. Min Act: -0.1700
Data Index: 1212659 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.1213. Min Act: -0.1700
Data Index: 8543600 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.0900. Min Act: -0.1700
Data Index: 8517620 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.0900. Min Act: -0.1700
Data Index: 1520545 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.0588. Min Act: -0.1700
Data Index: 6330275 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.0900. Min Act: -0.1700
Data Index: 5395960 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.0900. Min Act: -0.1700
Data Index: 1711001 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.0588. Min Act: -0.1700
Data Index: 6278989 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.0275. Min Act: -0.1700
Data Index: 1929169 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.0588. Min Act: -0.1700
Data Index: 3774486 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.0588. Min Act: -0.1700
Data Index: 3535279 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.0588. Min Act: -0.1700
Data Index: 3329687 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4963. Min Range: -5.4963
Max Act: 5.0275. Min Act: -0.1700
Data Index: 5320396 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19