Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4808. Min Act: -0.1700
Data Index: 6065114 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4652. Min Act: -0.1700
Data Index: 136169 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4652. Min Act: -0.1700
Data Index: 3891178 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4808. Min Act: -0.1700
Data Index: 6580554 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4652. Min Act: -0.1700
Data Index: 4074838 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4181. Min Act: -0.1700
Data Index: 2893192 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4338. Min Act: -0.1700
Data Index: 4954523 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4495. Min Act: -0.1700
Data Index: 6838312 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4025. Min Act: -0.1700
Data Index: 3937612 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4338. Min Act: -0.1700
Data Index: 2661114 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4181. Min Act: -0.1700
Data Index: 7934697 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4181. Min Act: -0.1700
Data Index: 3813784 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4338. Min Act: -0.1700
Data Index: 1994784 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.3868. Min Act: -0.1700
Data Index: 4337072 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4025. Min Act: -0.1700
Data Index: 1426577 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4025. Min Act: -0.1700
Data Index: 3340151 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4181. Min Act: -0.1700
Data Index: 4384585 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4181. Min Act: -0.1700
Data Index: 8516726 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.4025. Min Act: -0.1700
Data Index: 3635364 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4808. Min Range: -3.4808
Max Act: 3.3868. Min Act: -0.1700
Data Index: 8032493 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19