Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4041 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.1746. Min Act: -0.1700
Data Index: 2196522 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.1433. Min Act: -0.1700
Data Index: 4244541 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.1121. Min Act: -0.1700
Data Index: 2240224 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.0808. Min Act: -0.1700
Data Index: 1242725 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.1121. Min Act: -0.1700
Data Index: 4685995 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.0808. Min Act: -0.1700
Data Index: 7074134 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.0496. Min Act: -0.1700
Data Index: 8794098 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.0496. Min Act: -0.1700
Data Index: 8545518 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.0496. Min Act: -0.1700
Data Index: 6208169 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.0183. Min Act: -0.1700
Data Index: 6869956 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.0183. Min Act: -0.1700
Data Index: 6869957 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.0496. Min Act: -0.1700
Data Index: 7218707 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.0183. Min Act: -0.1700
Data Index: 8337926 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1746. Min Range: -5.1746
Max Act: 5.0183. Min Act: -0.1700
Data Index: 2848898 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1746. Min Range: -5.1746
Max Act: 4.9871. Min Act: -0.1700
Data Index: 497130 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1746. Min Range: -5.1746
Max Act: 4.9558. Min Act: -0.1700
Data Index: 1203434 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1746. Min Range: -5.1746
Max Act: 4.9871. Min Act: -0.1700
Data Index: 2576080 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1746. Min Range: -5.1746
Max Act: 4.9871. Min Act: -0.1700
Data Index: 3418789 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1746. Min Range: -5.1746
Max Act: 4.9871. Min Act: -0.1700
Data Index: 5780253 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1746. Min Range: -5.1746
Max Act: 4.9558. Min Act: -0.1700
Data Index: 7574858 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19