Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1617 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0975. Min Range: -10.0975
Max Act: 10.0975. Min Act: -0.1700
Data Index: 5898238 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.8475. Min Act: -0.1700
Data Index: 3768245 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.8475. Min Act: -0.1700
Data Index: 3018843 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.6600. Min Act: -0.1700
Data Index: 7196283 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.6600. Min Act: -0.1700
Data Index: 2097540 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.5975. Min Act: -0.1700
Data Index: 8368771 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.5975. Min Act: -0.1700
Data Index: 599966 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.5975. Min Act: -0.1700
Data Index: 3103008 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.5350. Min Act: -0.1700
Data Index: 2800014 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.4725. Min Act: -0.1700
Data Index: 1382182 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.4725. Min Act: -0.1700
Data Index: 1736225 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.4100. Min Act: -0.1700
Data Index: 3732563 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.4100. Min Act: -0.1700
Data Index: 4619415 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.4100. Min Act: -0.1700
Data Index: 6431827 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.4100. Min Act: -0.1700
Data Index: 2100837 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.4100. Min Act: -0.1700
Data Index: 4814430 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.4100. Min Act: -0.1700
Data Index: 7470960 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.3475. Min Act: -0.1700
Data Index: 6659831 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.3475. Min Act: -0.1700
Data Index: 2697166 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0975. Min Range: -10.0975
Max Act: 9.3475. Min Act: -0.1700
Data Index: 3787322 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19