Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1456 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.8957. Min Act: -0.1700
Data Index: 1577255 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.7707. Min Act: -0.1700
Data Index: 758974 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.7707. Min Act: -0.1700
Data Index: 1186653 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.7395. Min Act: -0.1700
Data Index: 972234 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.7082. Min Act: -0.1700
Data Index: 6490698 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.7082. Min Act: -0.1700
Data Index: 6990353 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.7082. Min Act: -0.1700
Data Index: 3977727 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.6770. Min Act: -0.1700
Data Index: 2004821 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.6457. Min Act: -0.1700
Data Index: 4286065 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.6770. Min Act: -0.1700
Data Index: 6634959 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.7082. Min Act: -0.1700
Data Index: 8381051 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.6770. Min Act: -0.1700
Data Index: 5817335 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.6457. Min Act: -0.1700
Data Index: 8576271 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.6457. Min Act: -0.1700
Data Index: 465281 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.6457. Min Act: -0.1700
Data Index: 487243 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.6145. Min Act: -0.1700
Data Index: 4016000 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.5832. Min Act: -0.1700
Data Index: 2609091 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.6145. Min Act: -0.1700
Data Index: 858917 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.6457. Min Act: -0.1700
Data Index: 2896390 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8957. Min Range: -5.8957
Max Act: 5.6145. Min Act: -0.1700
Data Index: 4024367 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19