Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5609 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.3825. Min Act: -0.1700
Data Index: 7971025 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.3200. Min Act: -0.1700
Data Index: 3784678 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.2888. Min Act: -0.1700
Data Index: 1174914 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.2263. Min Act: -0.1700
Data Index: 4630075 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.2263. Min Act: -0.1700
Data Index: 1959128 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1950. Min Act: -0.1700
Data Index: 3931028 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1638. Min Act: -0.1700
Data Index: 2153499 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1950. Min Act: -0.1700
Data Index: 1148353 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1950. Min Act: -0.1700
Data Index: 3013977 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1325. Min Act: -0.1700
Data Index: 6545104 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1638. Min Act: -0.1700
Data Index: 3374769 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1013. Min Act: -0.1700
Data Index: 5265409 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1325. Min Act: -0.1700
Data Index: 4846052 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1013. Min Act: -0.1700
Data Index: 3076969 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.0700. Min Act: -0.1700
Data Index: 8135711 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1013. Min Act: -0.1700
Data Index: 6734963 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1013. Min Act: -0.1700
Data Index: 8716193 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1325. Min Act: -0.1700
Data Index: 4646501 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1013. Min Act: -0.1700
Data Index: 6947621 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1013. Min Act: -0.1700
Data Index: 276812 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19