Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1964 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.8574. Min Act: -0.1700
Data Index: 462274 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.6699. Min Act: -0.1700
Data Index: 8669058 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.7949. Min Act: -0.1700
Data Index: 801804 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.6074. Min Act: -0.1700
Data Index: 5088113 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.6074. Min Act: -0.1700
Data Index: 3302120 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.5449. Min Act: -0.1700
Data Index: 7292404 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.6074. Min Act: -0.1700
Data Index: 2096342 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.4824. Min Act: -0.1700
Data Index: 3363638 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.5449. Min Act: -0.1700
Data Index: 4346392 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.4199. Min Act: -0.1700
Data Index: 616681 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.3574. Min Act: -0.1700
Data Index: 1419537 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.2949. Min Act: -0.1700
Data Index: 4650370 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.4199. Min Act: -0.1700
Data Index: 867932 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.2949. Min Act: -0.1700
Data Index: 2982850 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.3574. Min Act: -0.1700
Data Index: 161406 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.3574. Min Act: -0.1700
Data Index: 8137150 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.2949. Min Act: -0.1700
Data Index: 4063924 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.1699. Min Act: -0.1700
Data Index: 3236338 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.1699. Min Act: -0.1700
Data Index: 2672152 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8574. Min Range: -8.8574
Max Act: 8.1699. Min Act: -0.1700
Data Index: 3171377 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19