Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2860 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4946. Min Range: -5.4946
Max Act: 5.4946. Min Act: -0.1700
Data Index: 8058114 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4946. Min Range: -5.4946
Max Act: 5.1509. Min Act: -0.1700
Data Index: 416408 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4946. Min Range: -5.4946
Max Act: 5.1196. Min Act: -0.1700
Data Index: 8243967 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4946. Min Range: -5.4946
Max Act: 5.1196. Min Act: -0.1700
Data Index: 7744792 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4946. Min Range: -5.4946
Max Act: 5.0884. Min Act: -0.1700
Data Index: 2076024 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4946. Min Range: -5.4946
Max Act: 5.0884. Min Act: -0.1700
Data Index: 5805081 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4946. Min Range: -5.4946
Max Act: 5.0259. Min Act: -0.1700
Data Index: 5420150 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.9946. Min Act: -0.1700
Data Index: 4202688 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.9946. Min Act: -0.1700
Data Index: 5295326 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.9634. Min Act: -0.1700
Data Index: 6232796 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.9946. Min Act: -0.1700
Data Index: 5135335 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.9634. Min Act: -0.1700
Data Index: 7560460 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.9634. Min Act: -0.1700
Data Index: 718729 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.9321. Min Act: -0.1700
Data Index: 8540307 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.9321. Min Act: -0.1700
Data Index: 4855288 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.9321. Min Act: -0.1700
Data Index: 1967430 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.9634. Min Act: -0.1700
Data Index: 358457 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.8696. Min Act: -0.1700
Data Index: 5609153 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.9009. Min Act: -0.1700
Data Index: 5854272 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4946. Min Range: -5.4946
Max Act: 4.9009. Min Act: -0.1700
Data Index: 6772174 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19