Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4025 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.4969. Min Act: -0.1700
Data Index: 538627 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.4344. Min Act: -0.1700
Data Index: 1070061 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.4344. Min Act: -0.1700
Data Index: 6211011 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.4344. Min Act: -0.1700
Data Index: 1530655 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.4656. Min Act: -0.1700
Data Index: 6657636 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.4344. Min Act: -0.1700
Data Index: 221073 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.4031. Min Act: -0.1700
Data Index: 1267638 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.4344. Min Act: -0.1700
Data Index: 4231216 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.3719. Min Act: -0.1700
Data Index: 5349632 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.4031. Min Act: -0.1700
Data Index: 3652368 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.3719. Min Act: -0.1700
Data Index: 5593574 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.3719. Min Act: -0.1700
Data Index: 6921677 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.3406. Min Act: -0.1700
Data Index: 6525626 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.3719. Min Act: -0.1700
Data Index: 2936634 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.3406. Min Act: -0.1700
Data Index: 5141471 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.3406. Min Act: -0.1700
Data Index: 894981 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.3094. Min Act: -0.1700
Data Index: 1929945 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.3094. Min Act: -0.1700
Data Index: 2805718 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.3094. Min Act: -0.1700
Data Index: 4653711 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4969. Min Range: -4.4969
Max Act: 4.3094. Min Act: -0.1700
Data Index: 4743951 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19