Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3751 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.4747. Min Act: -0.1700
Data Index: 2255071 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.4434. Min Act: -0.1700
Data Index: 6788501 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.3497. Min Act: -0.1700
Data Index: 6824139 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.2872. Min Act: -0.1700
Data Index: 2243447 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.2559. Min Act: -0.1700
Data Index: 3840092 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.2559. Min Act: -0.1700
Data Index: 49833 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.2247. Min Act: -0.1700
Data Index: 6832515 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.1934. Min Act: -0.1700
Data Index: 5256220 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.1622. Min Act: -0.1700
Data Index: 5439242 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.1309. Min Act: -0.1700
Data Index: 3663105 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.1622. Min Act: -0.1700
Data Index: 5490287 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.1622. Min Act: -0.1700
Data Index: 7826305 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.1309. Min Act: -0.1700
Data Index: 3947843 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.1309. Min Act: -0.1700
Data Index: 5965064 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.0997. Min Act: -0.1700
Data Index: 3286636 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.1309. Min Act: -0.1700
Data Index: 3183132 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.0997. Min Act: -0.1700
Data Index: 5916394 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.0997. Min Act: -0.1700
Data Index: 3288263 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.0997. Min Act: -0.1700
Data Index: 6432272 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4747. Min Range: -5.4747
Max Act: 5.0997. Min Act: -0.1700
Data Index: 6539005 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19