Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5035 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1487. Min Range: -8.1487
Max Act: 8.1487. Min Act: -0.1700
Data Index: 5595747 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.9924. Min Act: -0.1700
Data Index: 1404082 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.8049. Min Act: -0.1700
Data Index: 8529555 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.7424. Min Act: -0.1700
Data Index: 8267108 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.7737. Min Act: -0.1700
Data Index: 4371362 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.7112. Min Act: -0.1700
Data Index: 2983193 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.7424. Min Act: -0.1700
Data Index: 8811251 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.6799. Min Act: -0.1700
Data Index: 1089696 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.6799. Min Act: -0.1700
Data Index: 3853913 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.6487. Min Act: -0.1700
Data Index: 8062015 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.5862. Min Act: -0.1699
Data Index: 8062017 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.5549. Min Act: -0.1700
Data Index: 8387215 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.4924. Min Act: -0.1700
Data Index: 4477393 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.4924. Min Act: -0.1700
Data Index: 2387658 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.4924. Min Act: -0.1699
Data Index: 8062018 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.4924. Min Act: -0.1700
Data Index: 2762669 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.4924. Min Act: -0.1700
Data Index: 8157969 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.4612. Min Act: -0.1700
Data Index: 6939558 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.4612. Min Act: -0.1700
Data Index: 7222471 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1487. Min Range: -8.1487
Max Act: 7.4299. Min Act: -0.1700
Data Index: 8062028 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19