Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1621 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.4908. Min Act: -0.1700
Data Index: 8051838 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.3971. Min Act: -0.1700
Data Index: 5463536 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.3346. Min Act: -0.1700
Data Index: 5615117 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.3033. Min Act: -0.1700
Data Index: 5848520 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.3033. Min Act: -0.1700
Data Index: 577439 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.3033. Min Act: -0.1700
Data Index: 6789089 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.2721. Min Act: -0.1700
Data Index: 4299331 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.2408. Min Act: -0.1700
Data Index: 2917618 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.2408. Min Act: -0.1700
Data Index: 5074297 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.2096. Min Act: -0.1700
Data Index: 2582448 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.2096. Min Act: -0.1700
Data Index: 1441182 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.1158. Min Act: -0.1700
Data Index: 870017 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.1471. Min Act: -0.1700
Data Index: 4080001 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.1158. Min Act: -0.1700
Data Index: 5074296 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.0533. Min Act: -0.1700
Data Index: 6124409 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.0533. Min Act: -0.1700
Data Index: 7375735 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.0533. Min Act: -0.1700
Data Index: 2021449 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.0221. Min Act: -0.1700
Data Index: 6687873 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.0221. Min Act: -0.1700
Data Index: 61118 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4908. Min Range: -6.4908
Max Act: 6.0221. Min Act: -0.1700
Data Index: 6061346 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19